JP7487318B2 - 3次元オブジェクトの多角形メッシュの生成のための自己回帰ニューラルネットワーク - Google Patents
3次元オブジェクトの多角形メッシュの生成のための自己回帰ニューラルネットワーク Download PDFInfo
- Publication number
- JP7487318B2 JP7487318B2 JP2022548004A JP2022548004A JP7487318B2 JP 7487318 B2 JP7487318 B2 JP 7487318B2 JP 2022548004 A JP2022548004 A JP 2022548004A JP 2022548004 A JP2022548004 A JP 2022548004A JP 7487318 B2 JP7487318 B2 JP 7487318B2
- Authority
- JP
- Japan
- Prior art keywords
- mesh
- token
- output
- generating
- neural network
- 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
Links
- 238000013528 artificial neural network Methods 0.000 title claims description 95
- 238000000034 method Methods 0.000 claims description 66
- 238000009826 distribution Methods 0.000 claims description 40
- 230000008569 process Effects 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 5
- 230000000873 masking effect Effects 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims 4
- 238000004519 manufacturing process Methods 0.000 description 19
- 238000004590 computer program Methods 0.000 description 13
- 238000009877 rendering Methods 0.000 description 12
- 230000009471 action Effects 0.000 description 9
- 239000000654 additive Substances 0.000 description 6
- 230000000996 additive effect Effects 0.000 description 6
- 239000003795 chemical substances by application Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 230000026676 system process Effects 0.000 description 5
- 230000003190 augmentative effect Effects 0.000 description 4
- 230000002787 reinforcement Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000001143 conditioned effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000000844 transformation Methods 0.000 description 2
- 241000009334 Singa Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
- G06T17/205—Re-meshing
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Description
102 コンテキスト入力
110 自己回帰メッシュ生成ニューラルネットワーク
150 出力シーケンス
152 3次元メッシュ
210 頂点生成ニューラルネットワーク
220 面生成ニューラルネットワーク
300 プロセス
400 プロセス
500 プロセス
Claims (26)
自己回帰メッシュ生成ニューラルネットワークを使用して、オブジェクトの3次元メッシュの頂点と面を指定する出力シーケンスを生成するステップであって、前記出力シーケンスが、複数の出力位置の各々においてそれぞれのメッシュトークンを備え、生成する前記ステップが、前記複数の出力位置のそれぞれにおいて、
前記出力位置の可能なメッシュトークンの確率分布を生成するために、任意の以前の出力位置においてすでに選択されている少なくとも任意のメッシュトークンに対して調整された前記自己回帰メッシュ生成ニューラルネットワークを使用して前記出力位置の入力を処理するステップと、
前記確率分布を使用して、前記出力位置の前記可能なメッシュトークンから前記出力位置において前記メッシュトークンを選択するステップと
を備える、方法。
前記確率分布からメッシュトークンをサンプリングするステップを備える、請求項1または2に記載の方法。
頂点エンコーダを使用して任意の以前の出力位置においてすでに選択されている任意の頂点座標のそれぞれの埋め込みを生成するステップと、
前記確率分布を生成するために前記頂点デコーダを使用して前記それぞれの埋め込みを処理するステップと
を備える、請求項4に記載の方法。
(i)前記複数の頂点の各々、(ii)新しい面トークン、および(iii)停止トークンのそれぞれのコンテキスト埋め込みを生成するステップと、
出力位置の前記第2のセットの各々において、
前記第2のセット内の任意の以前の出力位置において生成された各メッシュトークンのそれぞれの埋め込みを含むデコーダ入力を生成するステップと、
ポインタベクトルを生成するために、前記面デコーダを使用して前記デコーダ入力を処理するステップと、
前記ポインタベクトルと、(i)前記複数の頂点の各々、(ii)前記新しい面トークン、および(iii)前記停止トークンの前記それぞれのコンテキスト埋め込みから、(i)前記複数の頂点の各々、(ii)前記新しい面トークン、および(iii)前記停止トークンの確率分布を生成するステップと
を備える、請求項9に記載の方法。
前記面エンコーダを使用して(i)前記複数の頂点の各々、(ii)新しい面トークン、および(iii)停止トークンを処理するステップを備える、請求項10に記載の方法。
生成する前記ステップが、前記複数の出力位置の1つまたは複数において、
(i)任意の以前の出力位置においてすでに選択されている少なくとも任意のメッシュトークンに対して調整され、また(ii)前記出力位置の可能なメッシュトークンの確率分布を生成するために、前記コンテキスト入力に対して調整される、前記自己回帰メッシュ生成ニューラルネットワークを使用してタイムステップの入力を処理するステップを備える、請求項1から16のいずれか一項に記載の方法。
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202062971858P | 2020-02-07 | 2020-02-07 | |
US62/971,858 | 2020-02-07 | ||
PCT/EP2021/052984 WO2021156514A1 (en) | 2020-02-07 | 2021-02-08 | Autoregressive neural networks for the generation of polygonal meshes of 3d objects |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2023512721A JP2023512721A (ja) | 2023-03-28 |
JP7487318B2 true JP7487318B2 (ja) | 2024-05-20 |
Family
ID=74587022
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2022548004A Active JP7487318B2 (ja) | 2020-02-07 | 2021-02-08 | 3次元オブジェクトの多角形メッシュの生成のための自己回帰ニューラルネットワーク |
Country Status (6)
Country | Link |
---|---|
US (1) | US20230076437A1 (ja) |
EP (1) | EP4085429A1 (ja) |
JP (1) | JP7487318B2 (ja) |
KR (1) | KR102662672B1 (ja) |
CN (1) | CN115349141A (ja) |
WO (1) | WO2021156514A1 (ja) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210349444A1 (en) * | 2020-05-11 | 2021-11-11 | X Development Llc | Accelerating robotic planning for operating on deformable objects |
WO2023081095A1 (en) * | 2021-11-05 | 2023-05-11 | Subtle Medical, Inc. | Systems and methods for multi-contrast multi-scale vision transformers |
CN115908753B (zh) * | 2023-01-06 | 2023-05-19 | 粤港澳大湾区数字经济研究院(福田) | 一种全身人体网格表面重建方法及相关装置 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006318232A (ja) | 2005-05-12 | 2006-11-24 | Fuji Heavy Ind Ltd | 解析用メッシュ修正装置 |
JP2011243016A (ja) | 2010-05-19 | 2011-12-01 | Hitachi Ltd | 解析用メッシュ生成装置 |
US20200027269A1 (en) | 2018-07-23 | 2020-01-23 | Fudan University | Network, System and Method for 3D Shape Generation |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8797328B2 (en) * | 2010-07-23 | 2014-08-05 | Mixamo, Inc. | Automatic generation of 3D character animation from 3D meshes |
US11797839B2 (en) * | 2017-10-27 | 2023-10-24 | Google Llc | Training neural networks using priority queues |
CN111386537A (zh) * | 2017-10-27 | 2020-07-07 | 谷歌有限责任公司 | 基于注意力的仅解码器的序列转换神经网络 |
EP3732627A1 (en) * | 2018-02-09 | 2020-11-04 | Google LLC | Fast decoding in sequence models using discrete latent variables |
US10769848B1 (en) * | 2019-05-24 | 2020-09-08 | Adobe, Inc. | 3D object reconstruction using photometric mesh representation |
US11776210B2 (en) * | 2021-01-22 | 2023-10-03 | Sony Group Corporation | 3D face modeling based on neural networks |
-
2021
- 2021-02-08 CN CN202180023711.9A patent/CN115349141A/zh active Pending
- 2021-02-08 KR KR1020227030381A patent/KR102662672B1/ko active IP Right Grant
- 2021-02-08 WO PCT/EP2021/052984 patent/WO2021156514A1/en unknown
- 2021-02-08 EP EP21704483.3A patent/EP4085429A1/en active Pending
- 2021-02-08 JP JP2022548004A patent/JP7487318B2/ja active Active
- 2021-02-08 US US17/798,108 patent/US20230076437A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006318232A (ja) | 2005-05-12 | 2006-11-24 | Fuji Heavy Ind Ltd | 解析用メッシュ修正装置 |
JP2011243016A (ja) | 2010-05-19 | 2011-12-01 | Hitachi Ltd | 解析用メッシュ生成装置 |
US20200027269A1 (en) | 2018-07-23 | 2020-01-23 | Fudan University | Network, System and Method for 3D Shape Generation |
Non-Patent Citations (2)
Title |
---|
C.Nash et al.,PolyGen: An Autoregressive Generative Model of 3D Meshes,[online], arXiv:2002.10880v1,2020年02月23日,p.1-16,インターネット< https://arxiv.org/abs/2002.10880> |
S.Yongbin et al.,PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention,[online], arXiv: 1810.05591v3,2019年11月06日,p.1-8,インターネット< https://arxiv.org/abs/1810.05591> |
Also Published As
Publication number | Publication date |
---|---|
CN115349141A (zh) | 2022-11-15 |
KR20220138859A (ko) | 2022-10-13 |
EP4085429A1 (en) | 2022-11-09 |
JP2023512721A (ja) | 2023-03-28 |
KR102662672B1 (ko) | 2024-05-07 |
US20230076437A1 (en) | 2023-03-09 |
WO2021156514A1 (en) | 2021-08-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7487318B2 (ja) | 3次元オブジェクトの多角形メッシュの生成のための自己回帰ニューラルネットワーク | |
JP7295906B2 (ja) | ニューラルネットワークを使用したシーンの理解および生成 | |
CN111386536B (zh) | 语义一致的图像样式转换的方法和*** | |
JP7423828B2 (ja) | アテンションベースのシーケンス変換ニューラルネットワーク | |
JP7017640B2 (ja) | データ拡張方策の学習 | |
US11869147B2 (en) | Neural network for outputting a parameterized 3D model | |
CN110612538A (zh) | 生成输入数据项的离散潜在表示 | |
US11978268B2 (en) | Convex representation of objects using neural network | |
US20220058865A1 (en) | Variational auto-encoder for outputting a 3d model | |
US20240070972A1 (en) | Rendering new images of scenes using geometry-aware neural networks conditioned on latent variables | |
KR20240002898A (ko) | 3d 얼굴 재구성 모델 훈련 방법과 장치 및 3d 얼굴 형상 생성 방법과 장치 | |
WO2022069740A1 (en) | Simulating physical environments using mesh representations and graph neural networks | |
CN114708374A (zh) | 虚拟形象生成方法、装置、电子设备和存储介质 | |
CN117255998A (zh) | 使用空间和时间上的注意力对来自视频序列的对象表示的无监督学习 | |
CN114596203A (zh) | 用于生成图像和用于训练图像生成模型的方法和装置 | |
CN111868752B (zh) | 神经网络层权重的连续参数化 | |
Abdallah et al. | 3D web-based shape modelling: building up an adaptive architecture | |
US20230360327A1 (en) | Generating three-dimensional representations for digital objects utilizing mesh-based thin volumes | |
US20220164500A1 (en) | Intelligent assistants for computer-aided design | |
US20220058779A1 (en) | Inpainting method and apparatus for human image, and electronic device | |
KR20220035254A (ko) | 비대칭 신경망 | |
CN117611727A (zh) | 渲染处理方法、装置、设备以及介质 | |
CN115471613A (zh) | 人脸模型的生成方法、装置、设备及存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20221004 |
|
A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20231108 |
|
A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20231218 |
|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20240314 |
|
TRDD | Decision of grant or rejection written | ||
A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20240408 |
|
A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20240508 |
|
R150 | Certificate of patent or registration of utility model |
Ref document number: 7487318 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |