CN105681776B - A kind of method and apparatus of disparity map extraction - Google Patents

A kind of method and apparatus of disparity map extraction Download PDF

Info

Publication number
CN105681776B
CN105681776B CN201610019727.3A CN201610019727A CN105681776B CN 105681776 B CN105681776 B CN 105681776B CN 201610019727 A CN201610019727 A CN 201610019727A CN 105681776 B CN105681776 B CN 105681776B
Authority
CN
China
Prior art keywords
view image
pixel
parallax
dual
energy
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.)
Active
Application number
CN201610019727.3A
Other languages
Chinese (zh)
Other versions
CN105681776A (en
Inventor
李选中
宋呈群
吴振志
吴涵渠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Aoto Electronics Co Ltd
Original Assignee
Shenzhen Aoto Electronics Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Aoto Electronics Co Ltd filed Critical Shenzhen Aoto Electronics Co Ltd
Priority to CN201610019727.3A priority Critical patent/CN105681776B/en
Publication of CN105681776A publication Critical patent/CN105681776A/en
Application granted granted Critical
Publication of CN105681776B publication Critical patent/CN105681776B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
    • H04N13/106—Processing image signals
    • H04N13/128—Adjusting depth or disparity
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N2013/0074—Stereoscopic image analysis
    • H04N2013/0081—Depth or disparity estimation from stereoscopic image signals

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)

Abstract

The invention belongs to technical field of image processing, there is provided a kind of method and apparatus of disparity map extraction.Methods described includes:Dual-view image is read, and obtains the Pixel Information of the dual-view image；According to the Pixel Information, the parallax energy of respective pixel in the dual-view image is obtained；According to default parallax value, the parallax energy of the respective pixel of the dual-view image, to obtain the minimum parallax energy of the dual-view image, using parallax value corresponding to the minimum parallax energy as the pixel value of object pixel in disparity map.Disparity map can be automatically extracted according to dual-view image by the present invention, it is not necessary to which manual intervention, disparity map edge clear, quality are high.

Description

A kind of method and apparatus of disparity map extraction
Technical field
The invention belongs to technical field of image processing, more particularly to a kind of method and apparatus of disparity map extraction.
Background technology
At present, bore hole 3D display screen technology has evolved into ripe, but lacks the broadcasting content of multiple views picture.In order to solve this One problem, there has been proposed render new viewpoint image by one-view image and disparity map.However, how to obtain high quality Disparity map is a problem.
Therefore, it is necessary to a kind of new technical scheme is proposed, to solve above-mentioned technical problem.
The content of the invention
In consideration of it, the embodiment of the present invention provides a kind of method and apparatus of disparity map extraction, to obtain the parallax of high quality Figure.
The first aspect of the embodiment of the present invention, there is provided a kind of method of disparity map extraction, methods described include：
Dual-view image is read, and obtains the Pixel Information of the dual-view image；
According to the Pixel Information, the parallax energy of respective pixel in the dual-view image is obtained；
According to default parallax value, the parallax energy of the respective pixel of the dual-view image, to obtain the double vision The minimum parallax energy of figure image, using parallax value corresponding to the minimum parallax energy as the pixel of object pixel in disparity map Value.
The second aspect of the embodiment of the present invention, there is provided a kind of device of disparity map extraction, described device include：
Read module, obtain module and processing module；
The read module, for reading dual-view image, and obtain the Pixel Information of the dual-view image；
The acquisition module, for according to the Pixel Information, obtaining the parallax of respective pixel in the dual-view image Energy；
The processing module, for according to default parallax value, the parallax of the respective pixel of the dual-view image Amount, to obtain the minimum parallax energy of the dual-view image, using parallax value corresponding to the minimum parallax energy as parallax The pixel value of object pixel in figure.
Existing beneficial effect is the embodiment of the present invention compared with prior art：The embodiment of the present invention is according to default parallax Value, compare the parallax energy of the respective pixel of dual-view image, to obtain the minimum parallax energy of the dual-view image, by institute Pixel value of the parallax value as object pixel in disparity map corresponding to minimum parallax energy is stated, disparity map is automatically extracted out, is not required to Manual intervention is wanted, disparity map edge clear, quality are high, can further generate the virtual visual point image of high quality, solve multiple views Bore hole 3D film source scarcity problem.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art In the required accompanying drawing used be briefly described, it should be apparent that, drawings in the following description be only the present invention some Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these Accompanying drawing obtains other accompanying drawings.
Fig. 1 is the implementation process figure of the method for the disparity map extraction that the embodiment of the present invention one provides；
Fig. 2 is left view exemplary plot in the dual-view image that the embodiment of the present invention one provides；
Fig. 3 is right view exemplary plot in the dual-view image that the embodiment of the present invention one provides；
Fig. 4 is the disparity map exemplary plot by parallax energy harvesting that the embodiment of the present invention one provides；
Fig. 5 is the offer of the embodiment of the present invention one by the disparity map exemplary plot after bilateral filtering；
Fig. 6 is the composition schematic diagram of the device for the disparity map extraction that the embodiment of the present invention two provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and It is not used in the restriction present invention.
Embodiment one：
Fig. 1 shows the implementation process of the method for the disparity map extraction that the embodiment of the present invention one provides, the implementation process Details are as follows：
In step S101, dual-view image is read, and obtain the Pixel Information of the dual-view image；
In embodiments of the present invention, the dual-view image helps parallax stereogram for left and right or two pictures being arranged above and below Picture, if Fig. 2 is left view exemplary plot in dual-view image, Fig. 3 is right view exemplary plot in dual-view image.
In embodiments of the present invention, the Pixel Information of the dual-view image includes location of pixels and pixel value, the picture Element value is pixel grey scale.
In image digitazation, image is divided into the zonule of referred to as pictorial element, pictorial element abbreviation pixel, most often The division seen is to use square net, and each pixel has two attributes：Position and gray scale, location of pixels by square net row Determined with row, pixel grey scale is the integer of bright dark degree on the location of pixels, and tonal range is 0~255.
In step s 102, according to the Pixel Information, the parallax energy of respective pixel in the dual-view image is obtained；
Further, it is described according to the Pixel Information, obtain the parallax energy of respective pixel in the dual-view image Including：
According to the Pixel Information, pixel and the dual-view figure in the first view image are calculated in the dual-view image The pixel value difference square of the pixel of colleague's correspondence position as in the second view image, and using the pixel value difference square as The parallax energy of pixel and the pixel of the correspondence position of going together in the second view image in first view image.
Exemplary, the first row in the pixel of the first row first row in calculating the first view image and the second view image , can be using the pixel value difference square of the two pixels as parallax energy during the parallax energy of the pixel of secondary series.
Further, it is described according to the Pixel Information, obtain the parallax energy of respective pixel in the dual-view image Including：
According to the Pixel Information, multiple colleague's pixels and second view image in first view image are calculated The average value of the pixel value difference square of multiple colleague's pixels of middle colleague's correspondence position, and being averaged the pixel value difference square Value is as the multiple same of correspondence position that gone together in multiple colleague's pixels in first view image and second view image The parallax energy of row pixel.
Preferably, the multiple colleague's pixel is three colleague's pixels.
It is exemplary, the first row first row, three pixels of secondary series and the 3rd row and the in the first view image is calculated In two view images during the parallax energy of the first row secondary series, the 3rd row and three pixels of the 4th row, the first view image is calculated The pixel value difference square of middle the first row first row pixel and the first row secondary series pixel in the second view image, calculate the first view The pixel value difference square of the first row secondary series pixel and the row pixel of the first row the 3rd in the second view image in image, calculates first The pixel value difference square of the row pixel of the first row the 3rd and the row pixel of the first row the 4th in the second view image in view image, is calculated The average value of above three pixel value difference square, and using the average value of above three pixel value difference square as parallax energy.
Further, it is described according to the Pixel Information, obtain the parallax energy bag of respective pixel in the dual-view image Include：
According to the Pixel Information, pixel and second view image in the image block of first view image are calculated Colleague's image block in correspondence position pixel pixel value difference square average value, and by the average value of the pixel value difference square Parallax as correspondence position pixel in the image block of pixel in the image block of first view image and the second view image Energy.
Preferably, described image block is the image block of 3 × 3 pixels.
Exemplary, 3 × 3 images in the first view image is calculated using the first row first row pixel as first element When in block and the second view image using parallax energy of the first row first row pixel as 3 × 3 image blocks of first element, calculate The pixel value difference square of the first row first row pixel and the first row first row pixel in the second view image in first view image, The pixel of the first row secondary series pixel and the first row secondary series pixel in the second view image in the first view image is calculated successively The picture of squared difference the row pixel of the third line the 3rd and the row pixel of the third line the 3rd in the second view image into the first view image Nine pixel value differences square such as plain squared difference, calculate the average value of above-mentioned nine pixel value differences square, and by above-mentioned nine pictures The average value of plain squared difference is as parallax energy.
In step s 103, according to default parallax value, the parallax energy of the respective pixel of the dual-view image, with The minimum parallax energy of the dual-view image is obtained, using parallax value corresponding to the minimum parallax energy as mesh in disparity map Mark the pixel value of pixel.
In embodiments of the present invention, disparity map can be smoothed by bilateral filtering and/or medium filtering, retained The boundary information of disparity map, remove the noise in disparity map.
Disparity map be by dual-view image appoint piece image on the basis of, its size be the benchmark image size, pixel It is worth the image for parallax value, the parallax value is the interval of corresponding colleague's pixel in dual-view image, for example, in dual-view image The first row first row pixel and the first row first row pixel in the second view image in dual-view image in first view image Parallax value is 0, and the first row first row pixel regards with the first row secondary series pixel in the second view image in the first view image Difference is 1.
Exemplary, disparity map is on the basis of the left view in dual-view image, if Fig. 4 is by parallax energy harvesting Disparity map, Fig. 5 are by the disparity map after bilateral filtering.
Further, the default parallax value of the basis, the parallax energy of the respective pixel of the dual-view image, with The minimum parallax amount for obtaining the dual-view image specifically includes：
Inquire about the first view image and the second view image parallax value in the dual-view image in the dual-view image For 0 location of pixels, to obtain the parallax ENERGY E of the location of pixels0；
First view image is inquired about and the location of pixels that the second view image parallax value is 1, with described in acquisition The parallax ENERGY E of location of pixels1；
Compare the parallax ENERGY E0With the parallax ENERGY E1, and retain parallax value corresponding to current minimum parallax energy, Give up parallax value corresponding to current maximum disparity energy；
Increase by first view image and the second view image parallax value to default parallax value successively, search minimum Parallax value corresponding to parallax energy.
Exemplary, disparity map is on the basis of the first view image in dual-view image, with the first view image three Individual colleague's pixel and the average value of the pixel value difference square of three pixels of going together of correspondence position of being gone together in the second view image are made For parallax energy, the pixel position that the parallax value of the first view image and the second view image is 0 is searched in the second view image Put, and parallax ENERGY E corresponding to calculating0, parallax value be 1 location of pixels, and calculate corresponding to parallax ENERGY E1, compare parallax ENERGY E0With parallax ENERGY E1If parallax ENERGY E1Less than parallax ENERGY E0, then parallax ENERGY E is retained1, continuing search for parallax value is 2 location of pixels, and parallax ENERGY E corresponding to calculating2, compare parallax ENERGY E1With parallax ENERGY E2If parallax ENERGY E1It is less than Parallax ENERGY E2, then parallax ENERGY E is retained1, increase parallax value successively to default parallax value 40, it is corresponding to find minimum parallax energy Parallax value, and using parallax value corresponding to minimum parallax energy as the pixel value of object pixel in disparity map, the target picture Plain position is the second pixel position of three colleague's pixels in the first view image, i.e., the middle imago of described three colleagues pixel Plain position.
It should be noted that the view image of the embodiment of the present invention first refers to a certain view image, " first " is only herein Statement and the convenience referred to, it is not meant to necessarily to have corresponding first view in the specific implementation of the present invention Image.Similarly, " second " in the second view image is not meant at this also just for the sake of statement and the convenience referred to Corresponding second view image is necessarily had in the specific implementation of invention.
The embodiment of the present invention presets parallax value by basis, compares the parallax energy of the respective pixel of dual-view image, with The minimum parallax energy of the dual-view image is obtained, parallax value will be preset corresponding to the minimum parallax energy as disparity map The pixel value of middle object pixel, automatically extracts out disparity map, it is not necessary to manual intervention, and the disparity map is smoothed, Retain the marginal information of the disparity map, remove the noise in the disparity map, make the disparity map edge clear, quality high, one can be entered The virtual visual point image of step generation high quality, solves the problems, such as multiple views bore hole 3D film source scarcity.
Embodiment two：
Fig. 6 shows the composition schematic diagram of the device for the disparity map extraction that the embodiment of the present invention two provides, for the ease of saying It is bright, the part related to the embodiment of the present invention is illustrate only, details are as follows：
Read module 61, for reading dual-view image, and obtain the Pixel Information of the dual-view image；
Module 62 is obtained, for according to the Pixel Information, obtaining the parallax of respective pixel in the dual-view image Amount；
Further, the acquisition module 62 is used for：
According to the Pixel Information, pixel and the dual-view figure in the first view image are calculated in the dual-view image The pixel value difference square of the pixel of colleague's correspondence position as in the second view image, and using the pixel value difference square as The parallax energy of pixel and the pixel of the correspondence position of going together in the second view image in first view image.
Further, the acquisition module 62 is used for：
According to the Pixel Information, multiple colleague's pixels and second view image in first view image are calculated The average value of the pixel value difference square of multiple colleague's pixels of middle colleague's correspondence position, and being averaged the pixel value difference square Value is as the multiple same of correspondence position that gone together in multiple colleague's pixels in first view image and second view image The parallax energy of row pixel.
Preferably, the multiple colleague's pixel is three colleague's pixels.
Further, the acquisition module 62 is used for：
According to the Pixel Information, pixel and second view image in the image block of first view image are calculated Colleague's image block in correspondence position pixel pixel value difference square average value, and by the average value of the pixel value difference square Parallax as correspondence position pixel in the image block of pixel in the image block of first view image and the second view image Energy.
Preferably, described image block is the image block of 3 × 3 pixels.
Processing module 63, for according to default parallax value, the parallax energy of the respective pixel of the dual-view image, To obtain the minimum parallax energy of the dual-view image, using parallax value corresponding to the minimum parallax energy as in disparity map The pixel value of object pixel.
Preferably, the default parallax value is 40.
Further, the processing module 63 specifically includes：
First query unit 631, the second query unit 632, comparing unit 633 and processing unit 634；
First query unit 631, for inquiring about the first view image and the dual-view in the dual-view image The second view image parallax value is 0 location of pixels in image, to obtain the parallax ENERGY E of the location of pixels0；
Second query unit 632, for inquiring about first view image and the second view image parallax value For 1 location of pixels, to obtain the parallax ENERGY E of the location of pixels1；
The comparing unit 633, for the parallax ENERGY E0With the parallax ENERGY E1, and retain current minimum Parallax value corresponding to parallax energy, give up parallax value corresponding to current maximum disparity energy；
The processing unit 634, for increasing by first view image and the second view image parallax value successively To default parallax value, parallax value corresponding to minimum parallax energy is searched.
The device of disparity map extraction provided in an embodiment of the present invention can be used in foregoing corresponding embodiment of the method one, Details will not be repeated here referring to the description of above-described embodiment one.
The technical staff in the field can be understood that, for convenience and simplicity of description, only with above-mentioned each function The division progress of module, can be as needed and by above-mentioned function distribution by different function moulds for example, in practical application Block or unit are completed, i.e. the internal structure of described device is divided into different functional modules or unit, above-mentioned functional module or list Member can both be realized in the form of hardware, can also be realized in the form of software.In addition, the tool of each functional module or unit Body title is not limited to the protection domain of the application also only to facilitate be mutually distinguishable.
In summary, the embodiment of the present invention compares the parallax of the respective pixel of dual-view image according to default parallax value Amount, to obtain the minimum parallax energy of the dual-view image, will corresponding to the minimum parallax energy preset parallax value as The pixel value of object pixel, automatically extracts out disparity map in disparity map, it is not necessary to manual intervention, and the disparity map is carried out smooth Processing, retains the marginal information of the disparity map, removes the noise in the disparity map, makes the disparity map edge clear, quality high, can The virtual visual point image of high quality is further generated, solves the problems, such as multiple views bore hole 3D film source scarcity.
Those of ordinary skill in the art are further appreciated that all or part of step realized in above-described embodiment method is can To instruct the hardware of correlation to complete by program, described program can be stored in a computer read/write memory medium In, described storage medium, including ROM/RAM, disk, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.

Claims (8)

  1. A kind of 1. method of disparity map extraction, it is characterised in that methods described includes：
    Dual-view image is read, and obtains the Pixel Information of the dual-view image；
    According to the Pixel Information, the parallax energy of respective pixel in the dual-view image is obtained；
    According to default parallax value, the parallax energy of the respective pixel of the dual-view image, to obtain the dual-view figure The minimum parallax energy of picture, the pixel value using parallax value corresponding to the minimum parallax energy as object pixel in disparity map, Disparity map is smoothed by bilateral filtering and/or medium filtering, retains the boundary information of disparity map, removes disparity map In noise；The basis presets parallax value, the parallax energy of the respective pixel of the dual-view image, with described in acquisition The minimum parallax amount of dual-view image specifically includes：
    It is 0 to inquire about the first view image and the second view image parallax value in the dual-view image in the dual-view image Location of pixels, to obtain the parallax ENERGY E of the location of pixels0；
    First view image is inquired about and the location of pixels that the second view image parallax value is 1, to obtain the pixel The parallax ENERGY E of position1；
    Compare the parallax ENERGY E0With the parallax ENERGY E1, and retain currently parallax value corresponding to minimum parallax energy, give up Parallax value corresponding to current maximum disparity energy；
    Increase by first view image successively with the second view image parallax value to default parallax value, search minimum parallax Parallax value corresponding to energy.
  2. 2. according to the method for claim 1, it is characterised in that it is described according to the Pixel Information, obtain the dual-view The parallax energy of respective pixel includes in image：
    According to the Pixel Information, calculate in the dual-view image in the first view image pixel with the dual-view image The pixel value difference square of the pixel of colleague's correspondence position in second view image, and using the pixel value difference square as described in The parallax energy of pixel and the pixel of the correspondence position of going together in the second view image in first view image.
  3. 3. according to the method for claim 1, it is characterised in that it is described according to the Pixel Information, obtain the dual-view The parallax energy of respective pixel includes in image：
    According to the Pixel Information, calculate same in multiple go together pixels and second view images in first view image The average value of the pixel value difference square of multiple colleague's pixels of row correspondence position, and the average value of the pixel value difference square is made For multiple colleague's pixels in first view image and the multiple pictures of going together for correspondence position of being gone together in second view image The parallax energy of element.
  4. 4. according to the method for claim 1, it is characterised in that it is described according to the Pixel Information, obtain the dual-view The parallax energy of respective pixel includes in image：
    According to the Pixel Information, the same of pixel and second view image in the image block of first view image is calculated The average value of the pixel value difference square of correspondence position pixel in row image block, and using the average value of the pixel value difference square as The parallax energy of pixel and correspondence position pixel in the image block of the second view image in the image block of first view image.
  5. 5. a kind of device of disparity map extraction, it is characterised in that described device includes：
    Read module, obtain module and processing module；
    The read module, for reading dual-view image, and obtain the Pixel Information of the dual-view image；
    The acquisition module, for according to the Pixel Information, obtaining the parallax energy of respective pixel in the dual-view image；
    The processing module, for according to default parallax value, the parallax energy of the respective pixel of the dual-view image, with The minimum parallax energy of the dual-view image is obtained, using parallax value corresponding to the minimum parallax energy as mesh in disparity map The pixel value of pixel is marked, disparity map is smoothed by bilateral filtering and/or medium filtering, retains the border of disparity map Information, remove the noise in disparity map；
    The processing module specifically includes：
    First query unit, the second query unit, comparing unit and processing unit；
    First query unit, for inquiring about in the dual-view image in the first view image and the dual-view image the Two view image parallax values are 0 location of pixels, to obtain the parallax ENERGY E of the location of pixels0；
    Second query unit, for the picture for inquiring about first view image with the second view image parallax value is 1 Plain position, to obtain the parallax ENERGY E of the location of pixels1；
    The comparing unit, for the parallax ENERGY E0With the parallax ENERGY E1, and retain current minimum parallax energy Corresponding parallax value, give up parallax value corresponding to current maximum disparity energy；
    The processing unit, regarded for increasing by first view image successively with the second view image parallax value to default Difference, search parallax value corresponding to minimum parallax energy.
  6. 6. device according to claim 5, it is characterised in that the acquisition module is used for：
    According to the Pixel Information, calculate in the dual-view image in the first view image pixel with the dual-view image The pixel value difference square of the pixel of colleague's correspondence position in second view image, and using the pixel value difference square as described in The parallax energy of pixel and the pixel of the correspondence position of going together in the second view image in first view image.
  7. 7. device according to claim 5, it is characterised in that the acquisition module is used for：
    According to the Pixel Information, calculate same in multiple go together pixels and second view images in first view image The average value of the pixel value difference square of multiple colleague's pixels of row correspondence position, and the average value of the pixel value difference square is made For multiple colleague's pixels in first view image and the multiple pictures of going together for correspondence position of being gone together in second view image The parallax energy of element.
  8. 8. device according to claim 5, it is characterised in that the acquisition module is used for：
    According to the Pixel Information, the same of pixel and second view image in the image block of first view image is calculated The average value of the pixel value difference square of correspondence position pixel in row image block, and using the average value of the pixel value difference square as The parallax energy of pixel and correspondence position pixel in the image block of the second view image in the image block of first view image.
CN201610019727.3A 2016-01-13 2016-01-13 A kind of method and apparatus of disparity map extraction Active CN105681776B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610019727.3A CN105681776B (en) 2016-01-13 2016-01-13 A kind of method and apparatus of disparity map extraction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610019727.3A CN105681776B (en) 2016-01-13 2016-01-13 A kind of method and apparatus of disparity map extraction

Publications (2)

Publication Number Publication Date
CN105681776A CN105681776A (en) 2016-06-15
CN105681776B true CN105681776B (en) 2017-12-08

Family

ID=56300212

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610019727.3A Active CN105681776B (en) 2016-01-13 2016-01-13 A kind of method and apparatus of disparity map extraction

Country Status (1)

Country Link
CN (1) CN105681776B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11461942B2 (en) * 2018-12-21 2022-10-04 Koninklijke Kpn N.V. Generating and signaling transition between panoramic images
CN115022612B (en) * 2022-05-31 2024-01-09 北京京东方技术开发有限公司 Driving method and device of display device and display equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102609936A (en) * 2012-01-10 2012-07-25 四川长虹电器股份有限公司 Stereo image matching method based on belief propagation
CN103295223A (en) * 2012-02-27 2013-09-11 三星电子株式会社 Apparatus and method for estimating disparity using visibility energy model
CN104902254A (en) * 2014-03-03 2015-09-09 诺基亚公司 Method, apparatus and computer program product for disparity map estimation of stereo images
CN104980729A (en) * 2015-07-14 2015-10-14 上海玮舟微电子科技有限公司 Disparity map generation method and system
CN105007478A (en) * 2015-07-08 2015-10-28 南京信息工程大学 View synthesis method based on mean shift stereo matching

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102609936A (en) * 2012-01-10 2012-07-25 四川长虹电器股份有限公司 Stereo image matching method based on belief propagation
CN103295223A (en) * 2012-02-27 2013-09-11 三星电子株式会社 Apparatus and method for estimating disparity using visibility energy model
CN104902254A (en) * 2014-03-03 2015-09-09 诺基亚公司 Method, apparatus and computer program product for disparity map estimation of stereo images
CN105007478A (en) * 2015-07-08 2015-10-28 南京信息工程大学 View synthesis method based on mean shift stereo matching
CN104980729A (en) * 2015-07-14 2015-10-14 上海玮舟微电子科技有限公司 Disparity map generation method and system

Also Published As

Publication number Publication date
CN105681776A (en) 2016-06-15

Similar Documents

Publication Publication Date Title
EP2774124B1 (en) Depth-map generation for an input image using an example approximate depth-map associated with an example similar image
TWI524734B (en) Method and device for generating a depth map
CN102695064B (en) Real-time stereoscopic image generation device and method
US8711204B2 (en) Stereoscopic editing for video production, post-production and display adaptation
US20100073364A1 (en) Conversion method and apparatus with depth map generation
CN102665086B (en) Method for obtaining parallax by using region-based local stereo matching
KR20100135032A (en) Conversion device for two dimensional image to three dimensional image and method thereof
Jung et al. Depth sensation enhancement using the just noticeable depth difference
CN102271262B (en) Multithread-based video processing method for 3D (Three-Dimensional) display
TWI712990B (en) Method and apparatus for determining a depth map for an image, and non-transitory computer readable storage medium
Didyk et al. Apparent stereo: The cornsweet illusion can enhance perceived depth
CN102158725B (en) Stereoscopic image generation method and system
CN101610425A (en) A kind of method and apparatus of evaluating stereo image quality
Xu et al. Depth-aided exemplar-based hole filling for DIBR view synthesis
CN105719250A (en) Image inpainting method based on simple background, system and shooting camera
CN105657401A (en) Naked eye 3D display method and system and naked eye 3D display device
Hsu et al. Spatio-temporally consistent view synthesis from video-plus-depth data with global optimization
CN105681776B (en) A kind of method and apparatus of disparity map extraction
Jung A modified model of the just noticeable depth difference and its application to depth sensation enhancement
JP2015095779A (en) Image processing apparatus, image processing method, and electronic equipment
Liu et al. A retargeting method for stereoscopic 3D video
CN108848365B (en) A kind of reorientation stereo image quality evaluation method
CN105528772B (en) A kind of image interfusion method based on directiveness filtering
Cai et al. Hole-filling approach based on convolutional neural network for depth image-based rendering view synthesis
Kao Stereoscopic image generation with depth image based rendering

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP02 Change in the address of a patent holder

Address after: 518000 1805, tower 2, Shenye Jinyuan Building, No.112, Qingshuihe 1st Road, Qingshuihe community, Luohu District, Shenzhen City, Guangdong Province

Patentee after: SHENZHEN AOTO ELECTRONICS Co.,Ltd.

Address before: 518000 Guangdong city of Shenzhen province Nanshan District high tech Industrial Park building T2 A6-B

Patentee before: SHENZHEN AOTO ELECTRONICS Co.,Ltd.

CP02 Change in the address of a patent holder