JPWO2021225868A5 - - Google Patents
Download PDFInfo
- Publication number
- JPWO2021225868A5 JPWO2021225868A5 JP2023513265A JP2023513265A JPWO2021225868A5 JP WO2021225868 A5 JPWO2021225868 A5 JP WO2021225868A5 JP 2023513265 A JP2023513265 A JP 2023513265A JP 2023513265 A JP2023513265 A JP 2023513265A JP WO2021225868 A5 JPWO2021225868 A5 JP WO2021225868A5
- Authority
- JP
- Japan
- Prior art keywords
- mesh
- deformation
- vertex
- applying
- vertex offsets
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 claims 11
- 238000013528 artificial neural network Methods 0.000 claims 8
- 230000001815 facial effect Effects 0.000 claims 6
- 238000013527 convolutional neural network Methods 0.000 claims 4
- 238000013519 translation Methods 0.000 claims 1
- 230000014616 translation Effects 0.000 claims 1
Claims (18)
第1の複数のニューラルネットワークトレーニングモデルを適用することにより第1の複数の変形マップを生成するステップと、
第2の複数のニューラルネットワークトレーニングモデルを適用することにより第2の複数の変形マップを生成するステップであって、前記第2の複数の変形マップは、前記第1の複数の変形マップよりも大きい解像度を有する、ステップと、
前記第1の複数の変形マップに基づいて第1の複数の頂点オフセットを抽出するステップと、
前記第2の複数の変形マップに基づいて第2の複数の頂点オフセットを抽出するステップと、
前記顔モデルのメッシュ変形を生成するために前記第1の複数の頂点オフセット及び前記第2の複数の頂点オフセットを前記顔モデルのメッシュに適用するステップと、
を含む、方法。 1. A method for generating a mesh deformation of a face model, comprising:
generating a first plurality of deformation maps by applying a first plurality of neural network training models;
generating a second plurality of deformation maps by applying a second plurality of neural network training models, the second plurality of deformation maps having a greater resolution than the first plurality of deformation maps;
extracting a first plurality of vertex offsets based on the first plurality of deformation maps;
extracting a second plurality of vertex offsets based on the second plurality of deformation maps;
applying the first plurality of vertex offsets and the second plurality of vertex offsets to a mesh of the facial model to generate a mesh deformation of the facial model;
A method comprising:
前記第1の複数の頂点オフセットを前記メッシュの全ての頂点の値に適用するステップと、
前記メッシュ変形を生成するために前記第2の複数の頂点オフセットを前記メッシュの頂点の最大でもサブセットの値に適用するステップと、
を含む、請求項1に記載の方法。 The step of applying the first plurality of vertex offsets and the second plurality of vertex offsets to the mesh comprises:
applying the first plurality of vertex offsets to values of all vertices of the mesh;
applying the second plurality of vertex offsets to values of at most a subset of the vertices of the mesh to generate the mesh deformation;
The method of claim 1 , comprising:
複数の中間頂点値を生成するために前記第1の複数の頂点オフセットを前記メッシュの複数の頂点の値に追加するステップと、
前記メッシュ変形を生成するために前記第2の複数の頂点オフセットを前記複数の中間頂点値の最大でもサブセットに追加するステップと、
を含む、請求項1に記載の方法。 The step of applying the first plurality of vertex offsets and the second plurality of vertex offsets to the face model mesh comprises:
adding the first plurality of vertex offsets to values of a plurality of vertices of the mesh to generate a plurality of intermediate vertex values;
adding the second plurality of vertex offsets to at most a subset of the plurality of intermediate vertex values to generate the mesh deformation;
The method of claim 1 , comprising:
前記1又は2以上の剛体メッシュセグメントの各々の別個の近似を実行するステップと、
を更に含む、請求項1に記載の方法。 identifying one or more rigid mesh segments of the face model that move rigidly during deformation based on the first plurality of deformation maps and the second plurality of deformation maps;
performing a separate approximation of each of the one or more rigid mesh segments;
The method of claim 1 further comprising:
前記システムは、1又は2以上のプロセッサを含み、前記1又は2以上のプロセッサは、
第1の複数のニューラルネットワークトレーニングモデルを適用することによって第1の複数の変形マップを生成し、
第2の複数のニューラルネットワークトレーニングモデルを適用することによって第2の複数の変形マップを生成するように構成され、前記第2の複数の変形マップは、前記第1の複数の変形マップよりも大きい解像度を有し、
前記1又は2以上のプロセッサは、
前記第1の複数の変形マップに基づいて第1の複数の頂点オフセットを抽出し、
前記第2の複数の変形マップに基づいて第2の複数の頂点オフセットを抽出し、
前記顔モデルのメッシュ変形を生成するために前記第1の複数の頂点オフセット及び前記第2の複数の頂点オフセットを前記顔モデルのメッシュに適用する、
ように構成される、
システム。 1. A system for generating a mesh deformation of a face model, comprising:
The system includes one or more processors, the one or more processors:
generating a first plurality of deformation maps by applying a first plurality of neural network training models;
configured to generate a second plurality of deformation maps by applying a second plurality of neural network training models, the second plurality of deformation maps having a greater resolution than the first plurality of deformation maps;
The one or more processors:
Extracting a first plurality of vertex offsets based on the first plurality of deformation maps;
Extracting a second plurality of vertex offsets based on the second plurality of deformation maps;
applying the first plurality of vertex offsets and the second plurality of vertex offsets to a mesh of the facial model to generate a mesh deformation of the facial model.
It is configured as follows:
system.
前記第1の複数の頂点オフセットを前記メッシュの全ての頂点の値に適用すること、及び、
前記メッシュ変形を生成するために前記第2の複数の頂点オフセットを前記メッシュの頂点の最大でもサブセットの値に適用すること
によって、前記メッシュに前記第1の複数の頂点オフセット及び前記第2の複数の頂点オフセットを適用するように更に構成される、
請求項11に記載のシステム。 The one or more processors:
applying the first plurality of vertex offsets to values of all vertices of the mesh; and
and applying the first and second plurality of vertex offsets to the mesh by applying the second plurality of vertex offsets to values of at most a subset of the vertices of the mesh to generate the mesh deformation.
The system of claim 11.
前記命令は、
第1の複数のニューラルネットワークトレーニングモデルを適用することによって第1の複数の変形マップを生成することと、
第2の複数のニューラルネットワークトレーニングモデルを適用することによって第2の複数の変形マップを生成することであって、前記第2の複数の変形マップは、前記第1の複数の変形マップよりも大きい解像度を有する、生成することと、
前記第1の複数の変形マップに基づいて第1の複数の頂点オフセットを抽出することと、
前記第2の複数の変形マップに基づいて第2の複数の頂点オフセットを抽出することと、
前記顔モデルのメッシュ変形を生成するために前記第1の複数の頂点オフセット及び前記第2の複数の頂点オフセットを前記顔モデルのメッシュに適用することと、
を含む、機械可読な非一時的媒体。 1. A machine-readable, non-transitory medium having machine-executable instructions stored thereon for generating a mesh deformation of a face model, the medium comprising:
The instruction:
generating a first plurality of deformation maps by applying a first plurality of neural network training models;
generating a second plurality of deformation maps by applying a second plurality of neural network training models, the second plurality of deformation maps having a greater resolution than the first plurality of deformation maps;
extracting a first plurality of vertex offsets based on the first plurality of deformation maps;
extracting a second plurality of vertex offsets based on the second plurality of deformation maps;
applying the first plurality of vertex offsets and the second plurality of vertex offsets to a mesh of the facial model to generate a mesh deformation of the facial model;
(c) A machine-readable, non-transitory medium, including
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202063022398P | 2020-05-08 | 2020-05-08 | |
US63/022,398 | 2020-05-08 | ||
US17/065,423 US11348314B2 (en) | 2020-05-08 | 2020-10-07 | Fast and deep facial deformations |
US17/065,423 | 2020-10-07 | ||
PCT/US2021/030024 WO2021225868A1 (en) | 2020-05-08 | 2021-04-29 | Fast and deep facial deformations |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2023526566A JP2023526566A (en) | 2023-06-21 |
JPWO2021225868A5 true JPWO2021225868A5 (en) | 2024-05-14 |
Family
ID=78412975
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2023513265A Pending JP2023526566A (en) | 2020-05-08 | 2021-04-29 | fast and deep facial deformation |
Country Status (7)
Country | Link |
---|---|
US (2) | US11348314B2 (en) |
EP (1) | EP4147209A1 (en) |
JP (1) | JP2023526566A (en) |
KR (1) | KR20230009440A (en) |
CN (1) | CN115943436A (en) |
CA (1) | CA3176920A1 (en) |
WO (1) | WO2021225868A1 (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102675364B1 (en) * | 2017-07-28 | 2024-06-14 | 바오밥 스튜디오스, 인코포레이티드 | Systems and methods for real-time complex character animation and interactivity |
EP3671660A1 (en) * | 2018-12-20 | 2020-06-24 | Dassault Systèmes | Designing a 3d modeled object via user-interaction |
US11475608B2 (en) * | 2019-09-26 | 2022-10-18 | Apple Inc. | Face image generation with pose and expression control |
US11430247B2 (en) * | 2019-11-15 | 2022-08-30 | Snap Inc. | Image generation using surface-based neural synthesis |
US11348314B2 (en) | 2020-05-08 | 2022-05-31 | Dreamworks Animation Llc | Fast and deep facial deformations |
US11443484B2 (en) * | 2020-05-15 | 2022-09-13 | Microsoft Technology Licensing, Llc | Reinforced differentiable attribute for 3D face reconstruction |
US11875504B2 (en) * | 2020-09-10 | 2024-01-16 | Unity Technologies Sf | Systems and methods for building a muscle-to-skin transformation in computer animation |
US11941739B1 (en) * | 2021-01-05 | 2024-03-26 | Pixar | Object deformation network system and method |
US20220237879A1 (en) * | 2021-01-27 | 2022-07-28 | Facebook Technologies, Llc | Direct clothing modeling for a drivable full-body avatar |
US11941771B2 (en) * | 2021-02-03 | 2024-03-26 | Accenture Global Solutions Limited | Multi-dimensional model texture transfer |
CN115239860B (en) * | 2022-09-01 | 2023-08-01 | 北京达佳互联信息技术有限公司 | Expression data generation method and device, electronic equipment and storage medium |
CN115984440B (en) * | 2023-03-20 | 2023-06-27 | 腾讯科技(深圳)有限公司 | Object rendering method, device, computer equipment and storage medium |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6614428B1 (en) * | 1998-06-08 | 2003-09-02 | Microsoft Corporation | Compression of animated geometry using a hierarchical level of detail coder |
US20030043918A1 (en) * | 1999-12-20 | 2003-03-06 | Jiang Hong H. | Method and apparatus for performing video image decoding |
US8035643B2 (en) | 2007-03-19 | 2011-10-11 | Lucasfilm Entertainment Company Ltd. | Animation retargeting |
US8902232B2 (en) * | 2008-01-31 | 2014-12-02 | University Of Southern California | Facial performance synthesis using deformation driven polynomial displacement maps |
EP2370969A4 (en) * | 2008-12-04 | 2015-06-10 | Cubic Corp | System and methods for dynamically injecting expression information into an animated facial mesh |
US8614714B1 (en) | 2009-12-21 | 2013-12-24 | Lucasfilm Entertainment Company Ltd. | Combining shapes for animation |
US9508179B2 (en) * | 2013-07-19 | 2016-11-29 | Lucasfilm Entertainment Company Ltd. | Flexible 3-D character rigging development architecture |
CN104541306B (en) * | 2013-08-02 | 2019-10-25 | 索美智能有限公司 | Neurobehavioral animation system |
US9792723B2 (en) * | 2015-04-07 | 2017-10-17 | Disney Enterprises, Inc. | Method and system for progressively sculpting three-dimensional geometry |
US10586380B2 (en) * | 2016-07-29 | 2020-03-10 | Activision Publishing, Inc. | Systems and methods for automating the animation of blendshape rigs |
US10565792B2 (en) * | 2017-09-07 | 2020-02-18 | Dreamworks Animation Llc | Approximating mesh deformations for character rigs |
US10672164B2 (en) * | 2017-10-16 | 2020-06-02 | Adobe Inc. | Predicting patch displacement maps using a neural network |
US11069135B2 (en) * | 2019-03-07 | 2021-07-20 | Lucasfilm Entertainment Company Ltd. | On-set facial performance capture and transfer to a three-dimensional computer-generated model |
US11430564B2 (en) * | 2019-11-27 | 2022-08-30 | Shanghai United Imaging Intelligence Co., Ltd. | Personalized patient positioning, verification and treatment |
US11348314B2 (en) | 2020-05-08 | 2022-05-31 | Dreamworks Animation Llc | Fast and deep facial deformations |
-
2020
- 2020-10-07 US US17/065,423 patent/US11348314B2/en active Active
-
2021
- 2021-04-29 CN CN202180048571.0A patent/CN115943436A/en active Pending
- 2021-04-29 WO PCT/US2021/030024 patent/WO2021225868A1/en unknown
- 2021-04-29 CA CA3176920A patent/CA3176920A1/en active Pending
- 2021-04-29 KR KR1020227042975A patent/KR20230009440A/en active Search and Examination
- 2021-04-29 EP EP21728678.0A patent/EP4147209A1/en active Pending
- 2021-04-29 JP JP2023513265A patent/JP2023526566A/en active Pending
-
2022
- 2022-04-29 US US17/661,527 patent/US11875458B2/en active Active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JPWO2021225868A5 (en) | ||
Zhao et al. | Thin-plate spline motion model for image animation | |
KR102428176B1 (en) | Correction Method And Device for Distorted Document Image | |
US11222466B1 (en) | Three-dimensional geometry-based models for changing facial identities in video frames and images | |
Zhang et al. | Text-guided neural image inpainting | |
CN111161150A (en) | Image super-resolution reconstruction method based on multi-scale attention cascade network | |
JP2019091493A5 (en) | ||
Yang et al. | Biharmonic deformation transfer with automatic key point selection | |
CN110634105A (en) | Video high-space-time resolution signal processing method combining optical flow method and deep network | |
CN109410133B (en) | Face texture repairing method based on 3DMM | |
CN103985085A (en) | Image super-resolution amplifying method and device | |
CN116682120A (en) | Multilingual mosaic image text recognition method based on deep learning | |
KR20100088347A (en) | Method for retargeting expression | |
CN110992495A (en) | Virtual model deformation method and device | |
CN109447897B (en) | Real scene image synthesis method and system | |
CN112905737A (en) | Text error correction method, device, equipment and storage medium | |
CN111311479B (en) | FPGA-based character superposition method | |
CN107424119B (en) | Super-resolution method of single image | |
CN115797176A (en) | Image super-resolution reconstruction method | |
KR20220055970A (en) | Image Upscaling Apparatus And Method Based On Learning With Privileged Information | |
KR100974165B1 (en) | System and method for synthesis of face expression using nonlinear regression analysis | |
US11170550B2 (en) | Facial animation retargeting using an anatomical local model | |
KR100889854B1 (en) | Method and Apparatus for creating caricature Video | |
US20220327717A1 (en) | Jaw tracking without markers for facial performance capture | |
JP2011070283A (en) | Face image resolution enhancement device and program |