US20080152200A1 - 3d face reconstruction from 2d images - Google Patents
3d face reconstruction from 2d images Download PDFInfo
- Publication number
- US20080152200A1 US20080152200A1 US11/828,232 US82823207A US2008152200A1 US 20080152200 A1 US20080152200 A1 US 20080152200A1 US 82823207 A US82823207 A US 82823207A US 2008152200 A1 US2008152200 A1 US 2008152200A1
- Authority
- US
- United States
- Prior art keywords
- face
- images
- knowledge
- dimensional
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Definitions
- Point clouds corresponding to individual pairs are then merged into a single cloud, and outliers are removed at 145 .
- the dense feature detection is totally data driven, without using prior face knowledge or generic faces.
- 150 defines dense feature computation aids, used as simplifications to the dense feature matching. This may include outlier rejection techniques (such as tensor voting), and may include area search minimization.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Image Generation (AREA)
- Collating Specific Patterns (AREA)
Abstract
A 3D face reconstruction technique using 2D images, such as photographs of a face, is described. Prior face knowledge or a generic face is used to extract sparse 3D information from the images and to identify image pairs. Bundle adjustment is carried out to determine more accurate 3D camera positions, image pairs are rectified, and dense 3D face information is extracted without using the prior face knowledge. Outliers are removed, e.g., by using tensor voting. A 3D surface is extracted from the dense 3D information and surface detail is extracted from the images.
Description
- This application claims priority to U.S. patent application Ser. No. 11/669,099, filed on Jan. 30, 2007, which claims priority to U.S. Provisional Application 60/764,007, filed Jan. 31, 2006. The disclosure of the prior application is considered part of (and is incorporated by reference in) the disclosure of this application.
-
- The U.S. Government may have certain rights in this invention pursuant to Grant No. HMI-582-04-1-2002.
- Conventional face reconstruction techniques often use a two dimensional image or images (e.g. digital photographs) of a face to create a three dimensional representation of the face. The representation that is created may be a file, such as an electronic file, indicative of individual characteristics of different faces. The file can then be used, e.g., for facial recognition, animation, or rendering.
- The images, once obtained, are often processed based on prior knowledge or assumptions of what faces usually look like. This knowledge is often called “domain knowledge”, a “prior model”, or more specifically a “generic face”. For example, the prior face knowledge may indicate the presence or likely locations of different kinds of facial features, such as eyes, nose, etc. The prior face knowledge may assume that the face is formed of a linear combination of basis face shapes and appearances, camera parameters, lighting parameters, and other known elements, or elements that are susceptible of estimation. These elements can be combined to estimate the likely appearance of a face. More specifically, the domain knowledge may come in the form of a generic face shape defined by an artist or an average face shape computed from a plurality of known face shapes.
- One common technique for face reconstruction uses prior face knowledge of a generic face, and possibly a set of face metrics or deformation parameters, throughout the reconstruction process. Another common technique attempts to eschew the use of prior face knowledge and instead uses a purely data-driven approach to reconstruct the face. This can be done, for example, using triangulation of two-dimensional points in multiple images from multiple calibrated cameras. Unfortunately, the former approach may provide unrealistic data, due to the use of the generic face throughout the process. The latter approach requires additional hardware infrastructure which is difficult to practically implement at a reasonable cost. A single-camera purely data-driven approach alleviates some of the hardware constraints of multi-view stereo methods, but may itself be unstable due to the lack of constraints at stages of the process.
- The present application describes techniques for obtaining three-dimensional face information using an assisted technique. According to aspects, prior knowledge of face structure is used at some points during the processing operation, but other parts during the processing operation are purely data driven.
- Another operation uses a single camera for determination of 3D information from a set of 2D images.
-
FIG. 1 shows an overall flowchart of the operation; and -
FIG. 2 shows a general purpose computer which can carry out the flowchart. -
FIG. 3 shows how the three dimensional face tracker is assisted by a generic face. -
FIGS. 4A and 4B show the dense three dimensional features respectively embedded in a cylindrical space and unwrapped and triangulated. - The general structure and techniques, and more specific embodiments which can be used to effect different ways of carrying out the more general goals, are described herein.
- The present application refers to determining three dimensional information about an object, e.g., a face. Although the present embodiment is described with reference to 3D reconstruction and rendering of faces, it should be understood that these same techniques can be used to reconstruct and render multiple views of any object. When used for faces, the three dimensional information produced by the techniques disclosed herein can be used for any face based application, such as animation, recognition, or rendering. The techniques disclosed herein may be more realistic than other techniques that rely more extensively on prior knowledge of generic faces.
- The present inventors recognize that previous systems, which used strong prior knowledge of face appearance to reconstruct a face, in effect quantize the number of basis shapes that are used for forming and rendering the face. A strong prior knowledge or generic face approach is effectively limited by the degrees of freedom that are offered by the imposed prior face knowledge or generic face. Hence, the information and subsequent reconstructions do not capture all the subtle details in the original face.
- This “face space” quantization is caused because the prior knowledge and associated transformations limit the space of all possible faces that can be reconstructed by the system. Generic face or pure prior face knowledge based methods may not have sufficient degrees of freedom to cover the entire face space.
- An embodiment captures subtle face details by disregarding the prior face knowledge or generic face constraints at key points of the process, and instead by relying on the data using a data driven approach to find the details of the face called herein the dense features. The data-driven approach requires large amounts of data to deal effectively with noise, measurement uncertainties, and outliers. However, the present system does not use a purely data-driven approach, but also is assisted by methods that incorporate prior face knowledge or generic faces.
- According to one aspect, large amounts of data can be obtained from a single camera that operates to obtain multiple images. For example, this may use frames of video which collectively form a moving sequence of images. It may also be obtained from multiple different still images obtained from one or many cameras.
- U.S. Pat. No. 7,103,211 discloses a method for generating 3D face models, that uses no prior face knowledge whatsoever, but rather is completely data driven. The present system uses a system that is mostly data driven, but uses prior face knowledge or a generic face to determine certain parts of the information.
- An embodiment is disclosed with reference to the flowchart of
FIG. 1 .FIG. 1 also illustrates some exemplary thumbnail images, illustrating the operation. This flowchart can be carried out on any general purpose computer, such as the system shown inFIG. 2 . This system includes aprocessor 200, a user interface such as mouse andkeyboard 205, and adisplay screen 210. The computer can be, for example, an Intel-based processor or any other kind of processor. The computer receives raw or processed image data from one ormore cameras 215, e.g. still cameras or video cameras. Theprocessor 200 processes that raw image data according to the descriptions provided herein. As an alternative, the camera information may be stored in amemory 220, e.g. a hard drive, and processed at some later time. - An embodiment extracts information from a sequence of images, e.g. a video sequence, a sequence of stop motion style images from the video sequence, or simply a number of still images. Unless the subject is standing completely still and the camera does not change positions, the sequence of images will have multiple different views of the subject's head in the set of images.
- At 100, an initial pose estimation is determined. This may use a face tracking algorithm, such as that shown in
FIG. 3 , to derive an initial head pose estimate, and also to derive a mask which represents the look of the face. This uses prior knowledge of face structure to determine the likely position and pose of the head, location of facial features such as nose, mouth, etc, and the like.FIG. 3 illustrates 3 different poses in threedifferent images same face mask 300 is superimposed on each of those images. Theface mask 300 represents a generic face, and hence has spots for eyes, nose mouth, etc. In this way, the mask helps estimate the pose of the images. - The pose estimation technique passes a set of views to a sparse feature tracking module at 110. The views, which are passed to the module, are those which are believed to be good candidates for image pairs from which three dimensional information can be extracted. The sparse
feature tracking module 110 produces a set of feature correspondences for each image pair. The two images in a pair are sufficiently close so that these feature correspondences can be obtained. - Pose selection is carried out at 120, to select those images which properly make a pair that can be used for the determination of 3D information. These pairs should be close in pose and have similar lighting characteristics.
- Global optimization is performed over the entire set of feature points at 130. This is used to refine the camera position estimate and compute the three-dimensional structure of the sparse two dimensional features.
- The refined camera positions are used to rectify pairs of images at 135, thereby constraining the search space for corresponding feature points to a horizontal scan line in the paired images.
- At 140, dense feature matching is performed across the pairs. This finds additional features beyond the sparse detection that was carried out at 110. These correspondences are determined by triangulation using optimized camera poses to form a dense 3-D point cloud or disparity map.
- Point clouds corresponding to individual pairs are then merged into a single cloud, and outliers are removed at 145. The dense feature detection is totally data driven, without using prior face knowledge or generic faces. 150 defines dense feature computation aids, used as simplifications to the dense feature matching. This may include outlier rejection techniques (such as tensor voting), and may include area search minimization.
- At 155, the final cleaned point cloud is used to form a connected surface. A face texture is acquired from a frontal image. The final result is information representative of the surface. This can be a 3-D mesh formed of triangular patches. The final result can alternately be a set of 3D points or a surface defined for example by curve splines, subdivision surfaces, or other digital surface definitions.
- Further details about the operation are now provided.
- Conventional stereo reconstruction has relied on the existence of multiple cameras obtaining one or more similar image pairs. Feature correspondences between those multiple image pairs are determined. The feature correspondences are subsequently triangulated to find a final three-dimensional group of points.
- In an embodiment, a single camera is used to obtain multiple images, and then the images are recast as multi view stereo images. In an embodiment, the process assumes that the head is static and that the camera is moving or moved with respect to the head. While this is unlikely to be the case, this assumption provides no loss of generality; e.g., the camera can be static and the head moved, or both the camera and the head moved.
- As described above, the multiple images are first analyzed at 100 to determine an initial estimate of camera pose among the images. This initial estimate uses information indicative of a face, e.g. prior face knowledge or a generic face, to carry out the estimate. It provides “sparse” information that allows the system to determine enough information to find pose and correspondence between the images.
- For example, the initial estimates done with the prior face knowledge or generic face may provide information that indicates the perimeters of a face, the locations of a mask defining parts of the face, or other information. This provides information for image selection, and constrains the set of sparse features to be matched. Prior face knowledge or a generic face is used to form the sparse features, but the sparse features may be refined using data-driven optimization prior to dense features being determined.
- The tracker pose estimation module investigates the images to find similar images that can be rectified against one another. The similar images comprise images which define similar poses. This hence allows selection of a subset of images to be used for reconstruction. The images are selected using both the baseline information, as well as reliably tracked feature points across multiple images.
- There is always a measurement uncertainty between multiple different images. For example, as the angular baseline between a pair of images decreases, the error in the computed 3-D points is magnified. This decreased angular baseline hence increases 3-D measurement uncertainty. Less accurate 3D information can be obtained from images with smaller angular baselines between the images. As the angular baseline increases, more accurate 3D information can be extracted—however, there is also less surface area in common between the two views, and hence fewer possible matches. Image pairs are therefore selected to balance between the measurement uncertainty, and the number of errors. For example, images with 8 to 15 degrees of angular baseline and 6 points matched across the image pair, may be preferred.
- The balancing may be carried out by tracking feature points in multiple selected images. Only images which have high confidence matches (e.g., greater than 90%) between features are retained to establish feature chains. Frame pairs are maintained within the set of images if they meet the feature points and also meet a set baseline criteria. For example, the baseline criteria can be set—such as requiring at least 5 degrees of angular baseline. The feature point criterion also rejects frames that have highly inaccurate tracker pose estimates.
- This sparse matching phase produces a set of images and feature points that are matched across the sequence. Matches that are supported by this feature point matching are likely to be more accurate than matches which are solely predicted by the pose tracker. Feature point matches may also cover a greater number of frames than the tracker predicted matches—and hence provide more constraints on the camera pose refinement process. These constraints may result in greater accuracy in the pose refinement at 130.
- The bundle adjustment starts with the sets of images and feature points that are matched across the image set. These have been obtained, as described above, by the feature tracking. The bundle adjustment which is carried out at 130 is an optimization technique that solves for the camera parameters and for the 3-D positions of points based on two-dimensional correspondences between sets of images. The optimized parameters may include position and orientation of the camera and 3-D structure of the 2-D feature points. The optimization may be carried out by alternating a partial solution for structure, and then a partial solution for camera pose. A computer may alternatively carry out both of these calculations until an adequate solution converges.
- Bundle adjustment hence estimates the position of the camera in each image, by flip-flopping between estimating the pose of cameras and the position of points in an iterative fashion until it finally converges. The end result is a more accurate camera position as well as structure of the points. Because these are sparse “high confidence” points, it does not provide a full dense representation, but that is done in later stages.
- An alternative technique may simply iteratively change the values until good values are obtained.
- The 3-D locations of the matched feature points as estimated and
refined bundle adjustment 130 are used in the later stages to constrain the scope of the reconstruction. These form optimized camera poses that are used in all subsequent processing stages. - Dense feature matching 140 finds more information about corresponding points among the image pairs. An unconstrained dense matching, however, can be computationally prohibitive, since it can require a full image search for each match. An unconstrained search would compare each point in each image against each point in every other image.
- 150 generically represents the techniques that are used to reduce the scope of the dense feature search.
- According to an embodiment, an epipolar geometry technique is used. In epipolar geometry, each correspondent item must lie along a single line that extends between the paired or clustered images. The process can be further simplified by rectifying the images, such that each epipolar line coincides with a horizontal scan line. This avoids the need to re-sample the images for each potential match.
- After the rectification, corresponding points in each pair of images are found using a matching process. The prior face knowledge or generic face may be used to assist the matching process by restricting the matching to the area covered by the tracking face mask. This allows simplifying the search such that a template is extracted using a fixed window size for each pixel in one image. The template is matched along the corresponding epipolar line in the paired image.
- A minimum correlation threshold and restricted disparity range suitable for faces is used to reduce the number of spurious matches. Locations with a flat correlation plot or no obvious peak are rejected. However, multiple candidate matches may be maintained to find the best match.
- The result of the matching process is a disparity volume. Each (x,y,d) triplet maps a pixel (x,y) in one rectified image to a pixel (x+d,y) in a paired image.
- The known poses can be triangulated to convert disparity values to three dimensional points. Each disparity pixel is transformed to its original image space using the inverse of the rectifying transform. The three-dimensional location of that match is provided by the intersection between the rays passing through the camera's optical center and the corresponding feature matches in the image plane. In reality, errors in the feature matching and camera estimates will prevent these lines from intersecting exactly. The three-dimensional point that minimizes the orthogonal distance between the rays may be used.
- Another constraint may be provided by rejection of outliers in the derived structure. The three-dimensional result from the bundle adjustment process provides a more accurate, though sparse, estimate of the three-dimensional face structure. This is not sufficient to capture the subtle geometry of the face. In an embodiment, this is used to provide a constraint on the allowable three-dimensional computations in the dense reconstruction. Specifically, the computed structure should not deviate far from the bundle-adjustment-derived structure. This structure is first used to prefilter the data by converting the interpolated bundle-adjusted structure to voxels, and rejecting data at a predetermined distance from the voxels. In effect, this becomes a data optimization technique.
- The voxel testing removes the gross outliers, that is those which are more than a predetermined distance from the bundle voxels. It also removes boundary artifacts that are due to inaccurate placement of the face mask. Errors in feature matching, however, may result in reconstruction noise. If the noise is uncorrelated within the views and between the views, it will appear as sparse, high frequency variations in the three-dimensional structure. Correct matches however, will be correlated between views due to the smoothness and continuity of the face structure.
- Tensor voting may also be used to determine surface saliency and hence to maintain the correlation structure is tensor voting. A three-dimensional tensor voting scheme can be used to reinforce and determine the surface saliency. Tensor voting allows each 3-D point to be encoded as either a ball tensor, or a stick tensor. The information in the tensor is propagated to their neighbors via a voting operation. Neighbors which have similar structure therefore reinforce each other through the tensor voting process. The amount of the structural reinforcement is influenced by the initial structural saliency. This technique recovers a surface from the cloud of points.
- A good initial estimate of point normals may be preferred to blindly encoding the points as ball tensors. In an embodiment, the head is approximated by a cylinder as shown in
FIG. 4A . Cylinder normals are obtained. The cylinder normals may be used as the point normal approximations. -
FIG. 4B illustrates the same points unwrapped and triangulated. - In another embodiment, the system may use a 3×3 Eigensystem and may fix the normal as the first eigenvector in that Eigensystem. The remaining basis vectors may then be computed using singular value decomposition. Initial surface saliency, e.g. that defined by the difference in magnitude between the first two eigenvectors, may be set uniformly for all points.
- The 3D points obtained from the bundle adjustment are very accurate but sparse estimates of the facial structure. These points are added to the tensor voting point set with boosted surface saliency. Radial basis functions may also be used to interpolate a smooth surface between the 3D points obtained from the bundle adjustment. In this embodiment, normals for the 3D bundle points are computed from the interpolated surface, to use for the tensor voting. However, the interpolated surface itself is preferably not used for the tensor voting.
- After two passes of tensor voting, points with low surface saliency are removed, leaving a dense cloud of points distributed across the surface of the face.
- Prior face knowledge or a generic face may be introduced in the dense reconstruction stage such that the face space is not constrained. Specifically, an embodiment may use the prior face knowledge or a generic face in the dense process to determine and reject outliers e.g., based on proximity to an existing generic face representation, but is not used to compute or modify the 3D position of reconstructed points.
- The face detail is effectively captured in the three-dimensional point cloud. If the final goal is a mathematical description of the face, then the three-dimensional point cloud may be sufficient.
- An embodiment uses domain knowledge to generate and texture a mesh based on the dense three-dimensional structure. The embodiment operates to unwrap the 3-D point cloud onto a two-dimensional plane via a cylindrical projection. Following the cylindrical projection, each three-dimensional point cloud has a corresponding two-dimensional map location. The two-dimensional map locations may be triangulated using Delaunay triangulation. Their connectivity information is then transferred to the three-dimensional points, and the surface is defined according to the resulting mesh. The cylindrical unwrapping and triangulation is illustrated in
FIG. 4B . - The general structure and techniques, and more specific embodiments which can be used to effect different ways of carrying out the more general goals are described herein.
- Although only a few embodiments have been disclosed in detail above, other embodiments are possible and the inventors intend these to be encompassed within this specification. The specification describes specific examples to accomplish a more general goal that may be accomplished in another way. This disclosure is intended to be exemplary, and the claims are intended to cover any modification or alternative which might be predictable to a person having ordinary skill in the art. For example, many of the operations discussed herein refer to operations without using a generic face or prior face knowledge. It should be understood that these techniques alternately can be carried out using such a generic face or prior face knowledge, for some, but not all, of these techniques.
- Also, the inventors intend that only those claims which use the words “means for” are intended to be interpreted under 35 USC 112, sixth paragraph. Moreover, no limitations from the specification are intended to be read into any claims, unless those limitations are expressly included in the claims. The computers described herein may be any kind of computer, either general purpose, or some specific purpose computer such as a workstation. The computer may be a Pentium class computer, running windows XP or Linux, or may be a Macintosh computer. The computer may also be a handheld computer, such as a PDA, cellphone, or laptop.
- The programs may be written in C, or Java, Brew or any other programming language. The programs may be resident on a storage medium, e.g., magnetic or optical, e.g. the computer hard drive, a removable disk or media such as a memory stick or SD media, or other removable medium. The programs may also be run over a network, for example, with a server or other machine sending signals to the local machine, which allows the local machine to carry out the operations described herein.
- Where a specific numerical value is mentioned herein, it should be considered the value may be increased or decreased by 20%, while still staying within the teachings of the present application, unless some different range is specifically mentioned.
Claims (1)
1. A face reconstruction method, comprising:
analyzing a plurality of images of a face to find sparse, three-dimensional face features using prior knowledge of a face; and
using said sparse three-dimensional face features to analyze said plurality of images, to find dense three-dimensional features using a data driven approach, without using any prior knowledge.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/828,232 US20080152200A1 (en) | 2006-01-31 | 2007-07-25 | 3d face reconstruction from 2d images |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US76400706P | 2006-01-31 | 2006-01-31 | |
US11/669,099 US7856125B2 (en) | 2006-01-31 | 2007-01-30 | 3D face reconstruction from 2D images |
US11/828,232 US20080152200A1 (en) | 2006-01-31 | 2007-07-25 | 3d face reconstruction from 2d images |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/669,099 Continuation US7856125B2 (en) | 2006-01-31 | 2007-01-30 | 3D face reconstruction from 2D images |
Publications (1)
Publication Number | Publication Date |
---|---|
US20080152200A1 true US20080152200A1 (en) | 2008-06-26 |
Family
ID=38334107
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/669,099 Expired - Fee Related US7856125B2 (en) | 2006-01-31 | 2007-01-30 | 3D face reconstruction from 2D images |
US11/828,232 Abandoned US20080152200A1 (en) | 2006-01-31 | 2007-07-25 | 3d face reconstruction from 2d images |
US11/828,214 Expired - Fee Related US8126261B2 (en) | 2006-01-31 | 2007-07-25 | 3D face reconstruction from 2D images |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/669,099 Expired - Fee Related US7856125B2 (en) | 2006-01-31 | 2007-01-30 | 3D face reconstruction from 2D images |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/828,214 Expired - Fee Related US8126261B2 (en) | 2006-01-31 | 2007-07-25 | 3D face reconstruction from 2D images |
Country Status (5)
Country | Link |
---|---|
US (3) | US7856125B2 (en) |
EP (1) | EP1982292A4 (en) |
JP (1) | JP2009525543A (en) |
KR (1) | KR20080108430A (en) |
WO (1) | WO2008013575A2 (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090110244A1 (en) * | 2007-10-25 | 2009-04-30 | Electronic Data Systems Corporation | Apparatus, and associated method, for displaying data using data painting of an asymmetrical facial image |
US20090132371A1 (en) * | 2007-11-20 | 2009-05-21 | Big Stage Entertainment, Inc. | Systems and methods for interactive advertising using personalized head models |
US20100013832A1 (en) * | 2008-07-16 | 2010-01-21 | Jing Xiao | Model-Based Object Image Processing |
US20100215255A1 (en) * | 2009-02-25 | 2010-08-26 | Jing Xiao | Iterative Data Reweighting for Balanced Model Learning |
US20100214289A1 (en) * | 2009-02-25 | 2010-08-26 | Jing Xiao | Subdivision Weighting for Robust Object Model Fitting |
US20100214290A1 (en) * | 2009-02-25 | 2010-08-26 | Derek Shiell | Object Model Fitting Using Manifold Constraints |
US20100214288A1 (en) * | 2009-02-25 | 2010-08-26 | Jing Xiao | Combining Subcomponent Models for Object Image Modeling |
US7856125B2 (en) | 2006-01-31 | 2010-12-21 | University Of Southern California | 3D face reconstruction from 2D images |
US8447098B1 (en) | 2010-08-20 | 2013-05-21 | Adobe Systems Incorporated | Model-based stereo matching |
CN104142978A (en) * | 2014-07-14 | 2014-11-12 | 重庆邮电大学 | Image retrieval system and image retrieval method based on multi-feature and sparse representation |
CN104581047A (en) * | 2014-12-15 | 2015-04-29 | 苏州福丰科技有限公司 | Three-dimensional face recognition method for supervisory video recording |
US9208608B2 (en) | 2012-05-23 | 2015-12-08 | Glasses.Com, Inc. | Systems and methods for feature tracking |
US9236024B2 (en) | 2011-12-06 | 2016-01-12 | Glasses.Com Inc. | Systems and methods for obtaining a pupillary distance measurement using a mobile computing device |
US9286715B2 (en) | 2012-05-23 | 2016-03-15 | Glasses.Com Inc. | Systems and methods for adjusting a virtual try-on |
US9483853B2 (en) | 2012-05-23 | 2016-11-01 | Glasses.Com Inc. | Systems and methods to display rendered images |
CN107730519A (en) * | 2017-09-11 | 2018-02-23 | 广东技术师范学院 | A kind of method and system of face two dimensional image to face three-dimensional reconstruction |
WO2018136106A1 (en) * | 2017-01-17 | 2018-07-26 | Facebook, Inc. | Three-dimensional scene reconstruction from set of two-dimensional images for consumption in virtual reality |
US11170571B2 (en) * | 2019-11-15 | 2021-11-09 | Lucasfilm Entertainment Company Ltd. LLC | Obtaining high resolution and dense reconstruction of face from sparse facial markers |
Families Citing this family (118)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7804997B2 (en) * | 2004-06-10 | 2010-09-28 | Technest Holdings, Inc. | Method and system for a three dimensional facial recognition system |
US9330324B2 (en) | 2005-10-11 | 2016-05-03 | Apple Inc. | Error compensation in three-dimensional mapping |
CN101288105B (en) | 2005-10-11 | 2016-05-25 | 苹果公司 | For the method and system of object reconstruction |
CN101496033B (en) | 2006-03-14 | 2012-03-21 | 普莱姆森斯有限公司 | Depth-varying light fields for three dimensional sensing |
US20110071804A1 (en) * | 2007-02-21 | 2011-03-24 | Yiling Xie | Method And The Associated Mechanism For 3-D Simulation Stored-Image Database-Driven Spectacle Frame Fitting Services Over Public Network |
TWI433052B (en) * | 2007-04-02 | 2014-04-01 | Primesense Ltd | Depth mapping using projected patterns |
US20080281182A1 (en) * | 2007-05-07 | 2008-11-13 | General Electric Company | Method and apparatus for improving and/or validating 3D segmentations |
US8494252B2 (en) * | 2007-06-19 | 2013-07-23 | Primesense Ltd. | Depth mapping using optical elements having non-uniform focal characteristics |
JP5018404B2 (en) * | 2007-11-01 | 2012-09-05 | ソニー株式会社 | Image identification apparatus, image identification method, and program |
US8737721B2 (en) | 2008-05-07 | 2014-05-27 | Microsoft Corporation | Procedural authoring |
US8401276B1 (en) * | 2008-05-20 | 2013-03-19 | University Of Southern California | 3-D reconstruction and registration |
US8204299B2 (en) * | 2008-06-12 | 2012-06-19 | Microsoft Corporation | 3D content aggregation built into devices |
US8456517B2 (en) * | 2008-07-09 | 2013-06-04 | Primesense Ltd. | Integrated processor for 3D mapping |
US8289318B1 (en) * | 2008-08-29 | 2012-10-16 | Adobe Systems Incorporated | Determining three-dimensional shape characteristics in a two-dimensional image |
JP4613994B2 (en) * | 2008-09-16 | 2011-01-19 | ソニー株式会社 | Dynamic estimation device, dynamic estimation method, program |
US8704832B2 (en) | 2008-09-20 | 2014-04-22 | Mixamo, Inc. | Interactive design, synthesis and delivery of 3D character motion data through the web |
US8982122B2 (en) | 2008-11-24 | 2015-03-17 | Mixamo, Inc. | Real time concurrent design of shape, texture, and motion for 3D character animation |
US8659596B2 (en) | 2008-11-24 | 2014-02-25 | Mixamo, Inc. | Real time generation of animation-ready 3D character models |
US8462207B2 (en) * | 2009-02-12 | 2013-06-11 | Primesense Ltd. | Depth ranging with Moiré patterns |
US20100259547A1 (en) | 2009-02-12 | 2010-10-14 | Mixamo, Inc. | Web platform for interactive design, synthesis and delivery of 3d character motion data |
US8786682B2 (en) | 2009-03-05 | 2014-07-22 | Primesense Ltd. | Reference image techniques for three-dimensional sensing |
US8717417B2 (en) | 2009-04-16 | 2014-05-06 | Primesense Ltd. | Three-dimensional mapping and imaging |
WO2010134200A1 (en) * | 2009-05-22 | 2010-11-25 | 株式会社東芝 | Device, method and program for processing images |
US8547374B1 (en) * | 2009-07-24 | 2013-10-01 | Lockheed Martin Corporation | Detection and reconstruction of 3D objects with passive imaging sensors |
US9582889B2 (en) * | 2009-07-30 | 2017-02-28 | Apple Inc. | Depth mapping based on pattern matching and stereoscopic information |
US8803950B2 (en) * | 2009-08-24 | 2014-08-12 | Samsung Electronics Co., Ltd. | Three-dimensional face capturing apparatus and method and computer-readable medium thereof |
US8830227B2 (en) | 2009-12-06 | 2014-09-09 | Primesense Ltd. | Depth-based gain control |
US8644563B2 (en) * | 2009-12-14 | 2014-02-04 | Microsoft Corporation | Recognition of faces using prior behavior |
US8526684B2 (en) * | 2009-12-14 | 2013-09-03 | Microsoft Corporation | Flexible image comparison and face matching application |
EP2339537B1 (en) * | 2009-12-23 | 2016-02-24 | Metaio GmbH | Method of determining reference features for use in an optical object initialization tracking process and object initialization tracking method |
US9317970B2 (en) * | 2010-01-18 | 2016-04-19 | Disney Enterprises, Inc. | Coupled reconstruction of hair and skin |
US8982182B2 (en) | 2010-03-01 | 2015-03-17 | Apple Inc. | Non-uniform spatial resource allocation for depth mapping |
US20110222757A1 (en) | 2010-03-10 | 2011-09-15 | Gbo 3D Technology Pte. Ltd. | Systems and methods for 2D image and spatial data capture for 3D stereo imaging |
US8928672B2 (en) | 2010-04-28 | 2015-01-06 | Mixamo, Inc. | Real-time automatic concatenation of 3D animation sequences |
US8837774B2 (en) * | 2010-05-04 | 2014-09-16 | Bae Systems Information Solutions Inc. | Inverse stereo image matching for change detection |
CN101882326A (en) * | 2010-05-18 | 2010-11-10 | 广州市刑事科学技术研究所 | Three-dimensional craniofacial reconstruction method based on overall facial structure shape data of Chinese people |
US9135514B2 (en) * | 2010-05-21 | 2015-09-15 | Qualcomm Incorporated | Real time tracking/detection of multiple targets |
KR101176996B1 (en) * | 2010-06-29 | 2012-08-24 | 전남대학교산학협력단 | Method for detecting text line segmentation and apparatus for the same |
US9098931B2 (en) | 2010-08-11 | 2015-08-04 | Apple Inc. | Scanning projectors and image capture modules for 3D mapping |
EP2643659B1 (en) | 2010-11-19 | 2019-12-25 | Apple Inc. | Depth mapping using time-coded illumination |
US9131136B2 (en) | 2010-12-06 | 2015-09-08 | Apple Inc. | Lens arrays for pattern projection and imaging |
EP2650842A1 (en) | 2010-12-08 | 2013-10-16 | NEC Soft, Ltd. | Attribute value estimation device, attribute value estimation method, program, and recording medium |
US8274508B2 (en) | 2011-02-14 | 2012-09-25 | Mitsubishi Electric Research Laboratories, Inc. | Method for representing objects with concentric ring signature descriptors for detecting 3D objects in range images |
US9030528B2 (en) | 2011-04-04 | 2015-05-12 | Apple Inc. | Multi-zone imaging sensor and lens array |
JP2012234258A (en) * | 2011-04-28 | 2012-11-29 | Sony Corp | Image processing device, image processing method, and program |
CN102332087A (en) * | 2011-06-15 | 2012-01-25 | 夏东 | Face recognition method based on sparse representation |
US10049482B2 (en) | 2011-07-22 | 2018-08-14 | Adobe Systems Incorporated | Systems and methods for animation recommendations |
WO2013020248A1 (en) * | 2011-08-09 | 2013-02-14 | Intel Corporation | Image-based multi-view 3d face generation |
KR101229428B1 (en) * | 2011-08-22 | 2013-02-04 | 전남대학교산학협력단 | Method of global motion estimation using tensor voting |
WO2013074153A1 (en) | 2011-11-17 | 2013-05-23 | University Of Southern California | Generating three dimensional models from range sensor data |
US10748325B2 (en) | 2011-11-17 | 2020-08-18 | Adobe Inc. | System and method for automatic rigging of three dimensional characters for facial animation |
WO2013112749A1 (en) | 2012-01-24 | 2013-08-01 | University Of Southern California | 3d body modeling, from a single or multiple 3d cameras, in the presence of motion |
US9639959B2 (en) | 2012-01-26 | 2017-05-02 | Qualcomm Incorporated | Mobile device configured to compute 3D models based on motion sensor data |
JP5985661B2 (en) | 2012-02-15 | 2016-09-06 | アップル インコーポレイテッド | Scan depth engine |
US20130215113A1 (en) * | 2012-02-21 | 2013-08-22 | Mixamo, Inc. | Systems and methods for animating the faces of 3d characters using images of human faces |
US9747495B2 (en) | 2012-03-06 | 2017-08-29 | Adobe Systems Incorporated | Systems and methods for creating and distributing modifiable animated video messages |
JP5928010B2 (en) * | 2012-03-07 | 2016-06-01 | 株式会社豊田中央研究所 | Road marking detection apparatus and program |
US9418475B2 (en) | 2012-04-25 | 2016-08-16 | University Of Southern California | 3D body modeling from one or more depth cameras in the presence of articulated motion |
US20130287294A1 (en) * | 2012-04-30 | 2013-10-31 | Cywee Group Limited | Methods for Generating Personalized 3D Models Using 2D Images and Generic 3D Models, and Related Personalized 3D Model Generating System |
US8462155B1 (en) * | 2012-05-01 | 2013-06-11 | Google Inc. | Merging three-dimensional models based on confidence scores |
CN104704531B (en) | 2012-10-12 | 2017-09-12 | 皇家飞利浦有限公司 | For the system for the facial data for accessing object |
CN102999942B (en) * | 2012-12-13 | 2015-07-15 | 清华大学 | Three-dimensional face reconstruction method |
CN103108124B (en) * | 2012-12-28 | 2017-07-18 | 上海鼎为电子科技(集团)有限公司 | Image acquiring method, device and mobile terminal |
US9208382B2 (en) * | 2013-03-08 | 2015-12-08 | Trimble Navigation Limited | Methods and systems for associating a keyphrase with an image |
US10262462B2 (en) | 2014-04-18 | 2019-04-16 | Magic Leap, Inc. | Systems and methods for augmented and virtual reality |
US10095917B2 (en) | 2013-11-04 | 2018-10-09 | Facebook, Inc. | Systems and methods for facial representation |
US10203762B2 (en) | 2014-03-11 | 2019-02-12 | Magic Leap, Inc. | Methods and systems for creating virtual and augmented reality |
CN103984920B (en) * | 2014-04-25 | 2017-04-12 | 同济大学 | Three-dimensional face identification method based on sparse representation and multiple feature points |
CN103984922B (en) * | 2014-04-30 | 2017-04-26 | 苏亚 | Face identification method based on sparse representation and shape restriction |
BE1022215B1 (en) | 2014-05-09 | 2016-03-01 | Materialise N.V. | METHODS AND DEVICES FOR DESIGNING FOOTWEAR |
AU2015274283B2 (en) * | 2014-06-14 | 2020-09-10 | Magic Leap, Inc. | Methods and systems for creating virtual and augmented reality |
US10852838B2 (en) | 2014-06-14 | 2020-12-01 | Magic Leap, Inc. | Methods and systems for creating virtual and augmented reality |
US9619933B2 (en) | 2014-06-16 | 2017-04-11 | Occipital, Inc | Model and sizing information from smartphone acquired image sequences |
US9940727B2 (en) | 2014-06-19 | 2018-04-10 | University Of Southern California | Three-dimensional modeling from wide baseline range scans |
KR102238693B1 (en) | 2014-06-20 | 2021-04-09 | 삼성전자주식회사 | Method and apparatus for extracting feature regions in point cloud |
KR102025038B1 (en) * | 2014-09-11 | 2019-09-24 | 사이버옵틱스 코포레이션 | Point cloud merging from multiple cameras and sources in three-dimensional profilometry |
KR101997500B1 (en) | 2014-11-25 | 2019-07-08 | 삼성전자주식회사 | Method and apparatus for generating personalized 3d face model |
US9767620B2 (en) | 2014-11-26 | 2017-09-19 | Restoration Robotics, Inc. | Gesture-based editing of 3D models for hair transplantation applications |
US9734381B2 (en) * | 2014-12-17 | 2017-08-15 | Northrop Grumman Systems Corporation | System and method for extracting two-dimensional fingerprints from high resolution three-dimensional surface data obtained from contactless, stand-off sensors |
US10440350B2 (en) | 2015-03-03 | 2019-10-08 | Ditto Technologies, Inc. | Constructing a user's face model using particle filters |
WO2016183380A1 (en) * | 2015-05-12 | 2016-11-17 | Mine One Gmbh | Facial signature methods, systems and software |
EP3274986A4 (en) | 2015-03-21 | 2019-04-17 | Mine One GmbH | Virtual 3d methods, systems and software |
US10853625B2 (en) | 2015-03-21 | 2020-12-01 | Mine One Gmbh | Facial signature methods, systems and software |
US10082237B2 (en) | 2015-03-27 | 2018-09-25 | A9.Com, Inc. | Imaging system for imaging replacement parts |
US10429272B2 (en) * | 2015-09-30 | 2019-10-01 | Caterpillar Inc. | Command-driven automatic and semi-automatic mobile wear detection |
US10122996B2 (en) * | 2016-03-09 | 2018-11-06 | Sony Corporation | Method for 3D multiview reconstruction by feature tracking and model registration |
BR102016009093A2 (en) * | 2016-04-22 | 2017-10-31 | Sequoia Capital Ltda. | EQUIPMENT FOR ACQUISITION OF 3D IMAGE DATE OF A FACE AND AUTOMATIC METHOD FOR PERSONALIZED MODELING AND MANUFACTURE OF GLASS FRAMES |
US9686539B1 (en) | 2016-06-12 | 2017-06-20 | Apple Inc. | Camera pair calibration using non-standard calibration objects |
US10062198B2 (en) | 2016-06-23 | 2018-08-28 | LoomAi, Inc. | Systems and methods for generating computer ready animation models of a human head from captured data images |
US10559111B2 (en) | 2016-06-23 | 2020-02-11 | LoomAi, Inc. | Systems and methods for generating computer ready animation models of a human head from captured data images |
CN106203449A (en) * | 2016-07-08 | 2016-12-07 | 大连大学 | The approximation space clustering system of mobile cloud environment |
WO2018010101A1 (en) | 2016-07-12 | 2018-01-18 | Microsoft Technology Licensing, Llc | Method, apparatus and system for 3d face tracking |
CN107657653A (en) | 2016-07-25 | 2018-02-02 | 同方威视技术股份有限公司 | For the methods, devices and systems rebuild to the image of three-dimensional surface |
CN108010123B (en) * | 2017-11-23 | 2021-02-09 | 东南大学 | Three-dimensional point cloud obtaining method capable of retaining topology information |
US10643383B2 (en) | 2017-11-27 | 2020-05-05 | Fotonation Limited | Systems and methods for 3D facial modeling |
CN108710823B (en) * | 2018-04-09 | 2022-04-19 | 金陵科技学院 | Face similarity comparison method |
US10198845B1 (en) | 2018-05-29 | 2019-02-05 | LoomAi, Inc. | Methods and systems for animating facial expressions |
CN110689602A (en) * | 2018-06-20 | 2020-01-14 | 中兴通讯股份有限公司 | Three-dimensional face reconstruction method, device, terminal and computer readable storage medium |
CN110148468B (en) * | 2019-05-09 | 2021-06-29 | 北京航空航天大学 | Method and device for reconstructing dynamic face image |
CN110111418B (en) * | 2019-05-15 | 2022-02-25 | 北京市商汤科技开发有限公司 | Method and device for creating face model and electronic equipment |
US11551393B2 (en) | 2019-07-23 | 2023-01-10 | LoomAi, Inc. | Systems and methods for animation generation |
DE112020004391T5 (en) | 2019-09-17 | 2022-06-02 | Boston Polarimetrics, Inc. | SYSTEMS AND METHODS FOR SURFACE MODELING USING POLARIZATION FEATURES |
MX2022004163A (en) | 2019-10-07 | 2022-07-19 | Boston Polarimetrics Inc | Systems and methods for surface normals sensing with polarization. |
CN114787648B (en) | 2019-11-30 | 2023-11-10 | 波士顿偏振测定公司 | Systems and methods for transparent object segmentation using polarization cues |
CN111260597B (en) * | 2020-01-10 | 2021-12-03 | 大连理工大学 | Parallax image fusion method of multiband stereo camera |
US11195303B2 (en) | 2020-01-29 | 2021-12-07 | Boston Polarimetrics, Inc. | Systems and methods for characterizing object pose detection and measurement systems |
CN115428028A (en) | 2020-01-30 | 2022-12-02 | 因思创新有限责任公司 | System and method for synthesizing data for training statistical models in different imaging modalities including polarized images |
CN111462108B (en) * | 2020-04-13 | 2023-05-02 | 山西新华防化装备研究院有限公司 | Machine learning-based head-face product design ergonomics evaluation operation method |
WO2021243088A1 (en) | 2020-05-27 | 2021-12-02 | Boston Polarimetrics, Inc. | Multi-aperture polarization optical systems using beam splitters |
CN112684445B (en) * | 2020-12-02 | 2021-09-07 | 中国人民解放军国防科技大学 | MIMO-ISAR three-dimensional imaging method based on MD-ADMM |
CN112686202B (en) * | 2021-01-12 | 2023-04-25 | 武汉大学 | Human head identification method and system based on 3D reconstruction |
US12020455B2 (en) | 2021-03-10 | 2024-06-25 | Intrinsic Innovation Llc | Systems and methods for high dynamic range image reconstruction |
US11954886B2 (en) | 2021-04-15 | 2024-04-09 | Intrinsic Innovation Llc | Systems and methods for six-degree of freedom pose estimation of deformable objects |
US11290658B1 (en) | 2021-04-15 | 2022-03-29 | Boston Polarimetrics, Inc. | Systems and methods for camera exposure control |
CN113077552A (en) * | 2021-06-02 | 2021-07-06 | 北京道达天际科技有限公司 | DSM (digital communication system) generation method and device based on unmanned aerial vehicle image |
US11689813B2 (en) | 2021-07-01 | 2023-06-27 | Intrinsic Innovation Llc | Systems and methods for high dynamic range imaging using crossed polarizers |
EP4227903A1 (en) | 2022-02-14 | 2023-08-16 | Carl Zeiss Vision International GmbH | Method for head image registration and head model generation and corresponding devices |
WO2023219907A1 (en) | 2022-05-09 | 2023-11-16 | Materialise Nv | Methods and apparatuses for designing footwear |
Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4710873A (en) * | 1982-07-06 | 1987-12-01 | Marvin Glass & Associates | Video game incorporating digitized images of being into game graphics |
US5327521A (en) * | 1992-03-02 | 1994-07-05 | The Walt Disney Company | Speech transformation system |
US6141060A (en) * | 1996-10-22 | 2000-10-31 | Fox Sports Productions, Inc. | Method and apparatus for adding a graphic indication of a first down to a live video of a football game |
US6313835B1 (en) * | 1999-04-09 | 2001-11-06 | Zapa Digital Arts Ltd. | Simplified on-line preparation of dynamic web sites |
US6331861B1 (en) * | 1996-03-15 | 2001-12-18 | Gizmoz Ltd. | Programmable computer graphic objects |
US6350199B1 (en) * | 1999-03-16 | 2002-02-26 | International Game Technology | Interactive gaming machine and method with customized game screen presentation |
US6425825B1 (en) * | 1992-05-22 | 2002-07-30 | David H. Sitrick | User image integration and tracking for an audiovisual presentation system and methodology |
US20030007700A1 (en) * | 2001-07-03 | 2003-01-09 | Koninklijke Philips Electronics N.V. | Method and apparatus for interleaving a user image in an original image sequence |
US6539354B1 (en) * | 2000-03-24 | 2003-03-25 | Fluent Speech Technologies, Inc. | Methods and devices for producing and using synthetic visual speech based on natural coarticulation |
US6559845B1 (en) * | 1999-06-11 | 2003-05-06 | Pulse Entertainment | Three dimensional animation system and method |
US20040051783A1 (en) * | 2002-08-23 | 2004-03-18 | Ramalingam Chellappa | Method of three-dimensional object reconstruction from a video sequence using a generic model |
US20040070585A1 (en) * | 2000-11-13 | 2004-04-15 | Wolfgang Papiernik | Method and system for reconstructing a surface |
US20040208344A1 (en) * | 2000-03-09 | 2004-10-21 | Microsoft Corporation | Rapid computer modeling of faces for animation |
US20040223631A1 (en) * | 2003-05-07 | 2004-11-11 | Roman Waupotitsch | Face recognition based on obtaining two dimensional information from three-dimensional face shapes |
US20040223630A1 (en) * | 2003-05-05 | 2004-11-11 | Roman Waupotitsch | Imaging of biometric information based on three-dimensional shapes |
US20050111705A1 (en) * | 2003-08-26 | 2005-05-26 | Roman Waupotitsch | Passive stereo sensing for 3D facial shape biometrics |
US6919892B1 (en) * | 2002-08-14 | 2005-07-19 | Avaworks, Incorporated | Photo realistic talking head creation system and method |
US20050162419A1 (en) * | 2002-03-26 | 2005-07-28 | Kim So W. | System and method for 3-dimension simulation of glasses |
US20050226509A1 (en) * | 2004-03-30 | 2005-10-13 | Thomas Maurer | Efficient classification of three dimensional face models for human identification and other applications |
US7016824B2 (en) * | 2001-02-06 | 2006-03-21 | Geometrix, Inc. | Interactive try-on platform for eyeglasses |
US7027054B1 (en) * | 2002-08-14 | 2006-04-11 | Avaworks, Incorporated | Do-it-yourself photo realistic talking head creation system and method |
US7103211B1 (en) * | 2001-09-04 | 2006-09-05 | Geometrix, Inc. | Method and apparatus for generating 3D face models from one camera |
US7137892B2 (en) * | 1992-05-22 | 2006-11-21 | Sitrick David H | System and methodology for mapping and linking based user image integration |
US7697787B2 (en) * | 2002-06-06 | 2010-04-13 | Accenture Global Services Gmbh | Dynamic replacement of the face of an actor in a video movie |
Family Cites Families (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
IL113496A (en) | 1995-04-25 | 1999-09-22 | Cognitens Ltd | Apparatus and method for recreating and manipulating a 3d object based on a 2d projection thereof |
JP3512919B2 (en) * | 1995-09-18 | 2004-03-31 | 株式会社東芝 | Apparatus and method for restoring object shape / camera viewpoint movement |
AU6998996A (en) | 1995-10-08 | 1997-05-15 | Face Imaging Ltd. | A method for the automatic computerized audio visual dubbing of movies |
US6188776B1 (en) * | 1996-05-21 | 2001-02-13 | Interval Research Corporation | Principle component analysis of images for the automatic location of control points |
US6044168A (en) * | 1996-11-25 | 2000-03-28 | Texas Instruments Incorporated | Model based faced coding and decoding using feature detection and eigenface coding |
US6283858B1 (en) | 1997-02-25 | 2001-09-04 | Bgk International Incorporated | Method for manipulating images |
US6078701A (en) * | 1997-08-01 | 2000-06-20 | Sarnoff Corporation | Method and apparatus for performing local to global multiframe alignment to construct mosaic images |
AUPO894497A0 (en) | 1997-09-02 | 1997-09-25 | Xenotech Research Pty Ltd | Image processing method and apparatus |
US6047078A (en) * | 1997-10-03 | 2000-04-04 | Digital Equipment Corporation | Method for extracting a three-dimensional model using appearance-based constrained structure from motion |
WO1999060525A1 (en) * | 1998-05-15 | 1999-11-25 | Tricorder Technology Plc | Method and apparatus for 3d representation |
US6999073B1 (en) | 1998-07-20 | 2006-02-14 | Geometrix, Inc. | Method and system for generating fully-textured 3D |
US6553138B2 (en) * | 1998-12-30 | 2003-04-22 | New York University | Method and apparatus for generating three-dimensional representations of objects |
US7003134B1 (en) * | 1999-03-08 | 2006-02-21 | Vulcan Patents Llc | Three dimensional object pose estimation which employs dense depth information |
EP1039417B1 (en) * | 1999-03-19 | 2006-12-20 | Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V. | Method and device for the processing of images based on morphable models |
GB0004165D0 (en) | 2000-02-22 | 2000-04-12 | Digimask Limited | System for virtual three-dimensional object creation and use |
US7457457B2 (en) * | 2000-03-08 | 2008-11-25 | Cyberextruder.Com, Inc. | Apparatus and method for generating a three-dimensional representation from a two-dimensional image |
JP4341135B2 (en) * | 2000-03-10 | 2009-10-07 | コニカミノルタホールディングス株式会社 | Object recognition device |
US7224357B2 (en) | 2000-05-03 | 2007-05-29 | University Of Southern California | Three-dimensional modeling based on photographic images |
US6894686B2 (en) | 2000-05-16 | 2005-05-17 | Nintendo Co., Ltd. | System and method for automatically editing captured images for inclusion into 3D video game play |
JP3668769B2 (en) * | 2000-06-26 | 2005-07-06 | 独立行政法人産業技術総合研究所 | Method for calculating position / orientation of target object and method for calculating position / orientation of observation camera |
US6954498B1 (en) | 2000-10-24 | 2005-10-11 | Objectvideo, Inc. | Interactive video manipulation |
US6975750B2 (en) * | 2000-12-01 | 2005-12-13 | Microsoft Corp. | System and method for face recognition using synthesized training images |
US20020164068A1 (en) * | 2001-05-03 | 2002-11-07 | Koninklijke Philips Electronics N.V. | Model switching in a communication system |
JP2003030684A (en) * | 2001-07-10 | 2003-01-31 | Nippon Telegr & Teleph Corp <Ntt> | Face three-dimensional computer graphic generation method and device, face three-dimensional computer graphic generation program and storage medium storing face three-dimensional computer graphic generation program |
US7123263B2 (en) | 2001-08-14 | 2006-10-17 | Pulse Entertainment, Inc. | Automatic 3D modeling system and method |
US7634103B2 (en) * | 2001-10-01 | 2009-12-15 | L'oreal S.A. | Analysis using a three-dimensional facial image |
US7010158B2 (en) * | 2001-11-13 | 2006-03-07 | Eastman Kodak Company | Method and apparatus for three-dimensional scene modeling and reconstruction |
US6816159B2 (en) | 2001-12-10 | 2004-11-09 | Christine M. Solazzi | Incorporating a personalized wireframe image in a computer software application |
US7221809B2 (en) * | 2001-12-17 | 2007-05-22 | Genex Technologies, Inc. | Face recognition system and method |
JP2004147288A (en) * | 2002-10-25 | 2004-05-20 | Reallusion Inc | Facial image correction method |
US7212664B2 (en) * | 2003-08-07 | 2007-05-01 | Mitsubishi Electric Research Laboratories, Inc. | Constructing heads from 3D models and 2D silhouettes |
US7218774B2 (en) * | 2003-08-08 | 2007-05-15 | Microsoft Corp. | System and method for modeling three dimensional objects from a single image |
KR100682889B1 (en) * | 2003-08-29 | 2007-02-15 | 삼성전자주식회사 | Method and Apparatus for image-based photorealistic 3D face modeling |
JP4511147B2 (en) * | 2003-10-02 | 2010-07-28 | 株式会社岩根研究所 | 3D shape generator |
US7285047B2 (en) | 2003-10-17 | 2007-10-23 | Hewlett-Packard Development Company, L.P. | Method and system for real-time rendering within a gaming environment |
US8050491B2 (en) * | 2003-12-17 | 2011-11-01 | United Technologies Corporation | CAD modeling system and method |
JP2005309992A (en) * | 2004-04-23 | 2005-11-04 | Toyota Motor Corp | Image processor and image processing method |
CA2579903C (en) * | 2004-09-17 | 2012-03-13 | Cyberextruder.Com, Inc. | System, method, and apparatus for generating a three-dimensional representation from one or more two-dimensional images |
US7342587B2 (en) | 2004-10-12 | 2008-03-11 | Imvu, Inc. | Computer-implemented system and method for home page customization and e-commerce support |
JP4216824B2 (en) * | 2005-03-07 | 2009-01-28 | 株式会社東芝 | 3D model generation apparatus, 3D model generation method, and 3D model generation program |
US20060212353A1 (en) | 2005-03-16 | 2006-09-21 | Anton Roslov | Targeted advertising system and method |
US7415152B2 (en) | 2005-04-29 | 2008-08-19 | Microsoft Corporation | Method and system for constructing a 3D representation of a face from a 2D representation |
WO2006138525A2 (en) * | 2005-06-16 | 2006-12-28 | Strider Labs | System and method for recognition in 2d images using 3d class models |
US8615719B2 (en) | 2005-09-14 | 2013-12-24 | Jumptap, Inc. | Managing sponsored content for delivery to mobile communication facilities |
US7755619B2 (en) * | 2005-10-13 | 2010-07-13 | Microsoft Corporation | Automatic 3D face-modeling from video |
US20080007567A1 (en) | 2005-12-18 | 2008-01-10 | Paul Clatworthy | System and Method for Generating Advertising in 2D or 3D Frames and Scenes |
US7856125B2 (en) | 2006-01-31 | 2010-12-21 | University Of Southern California | 3D face reconstruction from 2D images |
US7720284B2 (en) | 2006-09-08 | 2010-05-18 | Omron Corporation | Method for outlining and aligning a face in face processing of an image |
US7870026B2 (en) | 2007-06-08 | 2011-01-11 | Yahoo! Inc. | Selecting and displaying advertisement in a personal media space |
-
2007
- 2007-01-30 US US11/669,099 patent/US7856125B2/en not_active Expired - Fee Related
- 2007-01-31 EP EP07835691.2A patent/EP1982292A4/en not_active Withdrawn
- 2007-01-31 KR KR1020087020957A patent/KR20080108430A/en not_active Application Discontinuation
- 2007-01-31 JP JP2008553359A patent/JP2009525543A/en active Pending
- 2007-01-31 WO PCT/US2007/002786 patent/WO2008013575A2/en active Application Filing
- 2007-07-25 US US11/828,232 patent/US20080152200A1/en not_active Abandoned
- 2007-07-25 US US11/828,214 patent/US8126261B2/en not_active Expired - Fee Related
Patent Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4710873A (en) * | 1982-07-06 | 1987-12-01 | Marvin Glass & Associates | Video game incorporating digitized images of being into game graphics |
US5327521A (en) * | 1992-03-02 | 1994-07-05 | The Walt Disney Company | Speech transformation system |
US6425825B1 (en) * | 1992-05-22 | 2002-07-30 | David H. Sitrick | User image integration and tracking for an audiovisual presentation system and methodology |
US7137892B2 (en) * | 1992-05-22 | 2006-11-21 | Sitrick David H | System and methodology for mapping and linking based user image integration |
US6331861B1 (en) * | 1996-03-15 | 2001-12-18 | Gizmoz Ltd. | Programmable computer graphic objects |
US6141060A (en) * | 1996-10-22 | 2000-10-31 | Fox Sports Productions, Inc. | Method and apparatus for adding a graphic indication of a first down to a live video of a football game |
US6350199B1 (en) * | 1999-03-16 | 2002-02-26 | International Game Technology | Interactive gaming machine and method with customized game screen presentation |
US6313835B1 (en) * | 1999-04-09 | 2001-11-06 | Zapa Digital Arts Ltd. | Simplified on-line preparation of dynamic web sites |
US6559845B1 (en) * | 1999-06-11 | 2003-05-06 | Pulse Entertainment | Three dimensional animation system and method |
US20040208344A1 (en) * | 2000-03-09 | 2004-10-21 | Microsoft Corporation | Rapid computer modeling of faces for animation |
US6539354B1 (en) * | 2000-03-24 | 2003-03-25 | Fluent Speech Technologies, Inc. | Methods and devices for producing and using synthetic visual speech based on natural coarticulation |
US20040070585A1 (en) * | 2000-11-13 | 2004-04-15 | Wolfgang Papiernik | Method and system for reconstructing a surface |
US7016824B2 (en) * | 2001-02-06 | 2006-03-21 | Geometrix, Inc. | Interactive try-on platform for eyeglasses |
US20030007700A1 (en) * | 2001-07-03 | 2003-01-09 | Koninklijke Philips Electronics N.V. | Method and apparatus for interleaving a user image in an original image sequence |
US7103211B1 (en) * | 2001-09-04 | 2006-09-05 | Geometrix, Inc. | Method and apparatus for generating 3D face models from one camera |
US20050162419A1 (en) * | 2002-03-26 | 2005-07-28 | Kim So W. | System and method for 3-dimension simulation of glasses |
US7697787B2 (en) * | 2002-06-06 | 2010-04-13 | Accenture Global Services Gmbh | Dynamic replacement of the face of an actor in a video movie |
US6919892B1 (en) * | 2002-08-14 | 2005-07-19 | Avaworks, Incorporated | Photo realistic talking head creation system and method |
US7027054B1 (en) * | 2002-08-14 | 2006-04-11 | Avaworks, Incorporated | Do-it-yourself photo realistic talking head creation system and method |
US20040051783A1 (en) * | 2002-08-23 | 2004-03-18 | Ramalingam Chellappa | Method of three-dimensional object reconstruction from a video sequence using a generic model |
US20040223630A1 (en) * | 2003-05-05 | 2004-11-11 | Roman Waupotitsch | Imaging of biometric information based on three-dimensional shapes |
US20040223631A1 (en) * | 2003-05-07 | 2004-11-11 | Roman Waupotitsch | Face recognition based on obtaining two dimensional information from three-dimensional face shapes |
US20050111705A1 (en) * | 2003-08-26 | 2005-05-26 | Roman Waupotitsch | Passive stereo sensing for 3D facial shape biometrics |
US20050226509A1 (en) * | 2004-03-30 | 2005-10-13 | Thomas Maurer | Efficient classification of three dimensional face models for human identification and other applications |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8126261B2 (en) | 2006-01-31 | 2012-02-28 | University Of Southern California | 3D face reconstruction from 2D images |
US7856125B2 (en) | 2006-01-31 | 2010-12-21 | University Of Southern California | 3D face reconstruction from 2D images |
US8064724B2 (en) * | 2007-10-25 | 2011-11-22 | Hewlett-Packard Development Company, L.P. | Apparatus, and associated method, for displaying data using data painting of an asymmetrical facial image |
US20090110244A1 (en) * | 2007-10-25 | 2009-04-30 | Electronic Data Systems Corporation | Apparatus, and associated method, for displaying data using data painting of an asymmetrical facial image |
US20090132371A1 (en) * | 2007-11-20 | 2009-05-21 | Big Stage Entertainment, Inc. | Systems and methods for interactive advertising using personalized head models |
US20090135177A1 (en) * | 2007-11-20 | 2009-05-28 | Big Stage Entertainment, Inc. | Systems and methods for voice personalization of video content |
US20090153552A1 (en) * | 2007-11-20 | 2009-06-18 | Big Stage Entertainment, Inc. | Systems and methods for generating individualized 3d head models |
US8730231B2 (en) | 2007-11-20 | 2014-05-20 | Image Metrics, Inc. | Systems and methods for creating personalized media content having multiple content layers |
US20100013832A1 (en) * | 2008-07-16 | 2010-01-21 | Jing Xiao | Model-Based Object Image Processing |
US8131063B2 (en) | 2008-07-16 | 2012-03-06 | Seiko Epson Corporation | Model-based object image processing |
US8260038B2 (en) | 2009-02-25 | 2012-09-04 | Seiko Epson Corporation | Subdivision weighting for robust object model fitting |
US20100214288A1 (en) * | 2009-02-25 | 2010-08-26 | Jing Xiao | Combining Subcomponent Models for Object Image Modeling |
US20100214290A1 (en) * | 2009-02-25 | 2010-08-26 | Derek Shiell | Object Model Fitting Using Manifold Constraints |
US8204301B2 (en) | 2009-02-25 | 2012-06-19 | Seiko Epson Corporation | Iterative data reweighting for balanced model learning |
US8208717B2 (en) | 2009-02-25 | 2012-06-26 | Seiko Epson Corporation | Combining subcomponent models for object image modeling |
US8260039B2 (en) | 2009-02-25 | 2012-09-04 | Seiko Epson Corporation | Object model fitting using manifold constraints |
US20100214289A1 (en) * | 2009-02-25 | 2010-08-26 | Jing Xiao | Subdivision Weighting for Robust Object Model Fitting |
US20100215255A1 (en) * | 2009-02-25 | 2010-08-26 | Jing Xiao | Iterative Data Reweighting for Balanced Model Learning |
US8447098B1 (en) | 2010-08-20 | 2013-05-21 | Adobe Systems Incorporated | Model-based stereo matching |
US9236024B2 (en) | 2011-12-06 | 2016-01-12 | Glasses.Com Inc. | Systems and methods for obtaining a pupillary distance measurement using a mobile computing device |
US9483853B2 (en) | 2012-05-23 | 2016-11-01 | Glasses.Com Inc. | Systems and methods to display rendered images |
US9208608B2 (en) | 2012-05-23 | 2015-12-08 | Glasses.Com, Inc. | Systems and methods for feature tracking |
US9235929B2 (en) | 2012-05-23 | 2016-01-12 | Glasses.Com Inc. | Systems and methods for efficiently processing virtual 3-D data |
US10147233B2 (en) | 2012-05-23 | 2018-12-04 | Glasses.Com Inc. | Systems and methods for generating a 3-D model of a user for a virtual try-on product |
US9286715B2 (en) | 2012-05-23 | 2016-03-15 | Glasses.Com Inc. | Systems and methods for adjusting a virtual try-on |
US9311746B2 (en) | 2012-05-23 | 2016-04-12 | Glasses.Com Inc. | Systems and methods for generating a 3-D model of a virtual try-on product |
US9378584B2 (en) | 2012-05-23 | 2016-06-28 | Glasses.Com Inc. | Systems and methods for rendering virtual try-on products |
CN104142978A (en) * | 2014-07-14 | 2014-11-12 | 重庆邮电大学 | Image retrieval system and image retrieval method based on multi-feature and sparse representation |
CN104581047A (en) * | 2014-12-15 | 2015-04-29 | 苏州福丰科技有限公司 | Three-dimensional face recognition method for supervisory video recording |
WO2018136106A1 (en) * | 2017-01-17 | 2018-07-26 | Facebook, Inc. | Three-dimensional scene reconstruction from set of two-dimensional images for consumption in virtual reality |
US10038894B1 (en) | 2017-01-17 | 2018-07-31 | Facebook, Inc. | Three-dimensional scene reconstruction from set of two dimensional images for consumption in virtual reality |
CN107730519A (en) * | 2017-09-11 | 2018-02-23 | 广东技术师范学院 | A kind of method and system of face two dimensional image to face three-dimensional reconstruction |
US11170571B2 (en) * | 2019-11-15 | 2021-11-09 | Lucasfilm Entertainment Company Ltd. LLC | Obtaining high resolution and dense reconstruction of face from sparse facial markers |
US20220058870A1 (en) * | 2019-11-15 | 2022-02-24 | Lucasfilm Entertainment Company Ltd. LLC | Obtaining high resolution and dense reconstruction of face from sparse facial markers |
US11783493B2 (en) * | 2019-11-15 | 2023-10-10 | Lucasfilm Entertainment Company Ltd. LLC | Obtaining high resolution and dense reconstruction of face from sparse facial markers |
Also Published As
Publication number | Publication date |
---|---|
KR20080108430A (en) | 2008-12-15 |
US8126261B2 (en) | 2012-02-28 |
US20080152213A1 (en) | 2008-06-26 |
JP2009525543A (en) | 2009-07-09 |
WO2008013575A2 (en) | 2008-01-31 |
EP1982292A2 (en) | 2008-10-22 |
US7856125B2 (en) | 2010-12-21 |
EP1982292A4 (en) | 2013-05-29 |
WO2008013575A3 (en) | 2008-06-19 |
US20070183653A1 (en) | 2007-08-09 |
WO2008013575A9 (en) | 2008-03-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8126261B2 (en) | 3D face reconstruction from 2D images | |
EP1072014B1 (en) | Face recognition from video images | |
Alvarez et al. | Dense disparity map estimation respecting image discontinuities: A PDE and scale-space based approach | |
US20180218507A1 (en) | 3d reconstruction of a human ear from a point cloud | |
Fidaleo et al. | Model-assisted 3d face reconstruction from video | |
US10839541B2 (en) | Hierarchical disparity hypothesis generation with slanted support windows | |
Matsumoto et al. | Shape-from-silhouette/stereo and its application to 3-d digitizer | |
Izquierdo | Stereo image analysis for multi-viewpoint telepresence applications | |
CN101395613A (en) | 3D face reconstruction from 2D images | |
KR20190069750A (en) | Enhancement of augmented reality using posit algorithm and 2d to 3d transform technique | |
Zucchelli et al. | Multiple Plane Segmentation Using Optical Flow. | |
Nicolescu et al. | A voting-based computational framework for visual motion analysis and interpretation | |
Nicolescu et al. | Layered 4D representation and voting for grouping from motion | |
EP1580684B1 (en) | Face recognition from video images | |
Nicosevici et al. | Online robust 3D mapping using structure from motion cues | |
Nicolescu et al. | Perceptual grouping from motion cues using tensor voting in 4-D | |
Izquierdo et al. | Modeling arbitrary objects based on geometric surface conformity | |
Ji et al. | A 3D shape constraint on video | |
Bronstein et al. | Facetoface: An isometric model for facial animation | |
Wang et al. | Deformable template based stereo | |
AU2004212509B2 (en) | Face recognition from video images | |
JP2023000111A (en) | Three-dimensional model restoration device, method, and program | |
CN114037804A (en) | Indoor scene reconstruction method combining body-level feature constraints | |
Kang et al. | Non-iterative approach to multiple 2D motion estimation | |
Agrawal et al. | Moving object segmentation and dynamic scene reconstruction using two frames |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SOUTHERN CALIFORNIA, UNIVERSITY OF, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MEDIONI, GERARD;FIDALEO, DOUGLAS;REEL/FRAME:025165/0687 Effective date: 20070412 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |