Deformation transfer survey

Abstract Deformation transfer is a type of retargeting method that operates directly on the mesh and, by doing so, enables reuse of animation without setting up character rigs and a mapping between the source and target geometries. Deformation transfer can potentially reduce the costs of animation and give studios a competitive edge when keeping up with the latest computer animation technology. Unfortunately, deformation transfer has limitations and is yet to become standard practice in the industry. This survey starts by introducing Sumner and Popovic’s [18] seminal work and highlights key issues for industry settings. We then review related work in sections, organized by these key issues. After surveying related work, we discuss how their advances open the door to several practical applications of deformation transfer. To conclude, we highlight areas of future work.

[1]  Kun Zhou,et al.  Deformation Transfer to Multi‐Component Objects , 2010, Comput. Graph. Forum.

[2]  Michael J. Black,et al.  Detailed Human Shape and Pose from Images , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Maks Ovsjanikov,et al.  Unsupervised Deep Learning for Structured Shape Matching , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Lin Gao,et al.  Biharmonic deformation transfer with automatic key point selection , 2018, Graph. Model..

[5]  Hujun Bao,et al.  Cage-based deformation transfer , 2010, Comput. Graph..

[6]  Christian Rössl,et al.  Harmonic Guidance for Surface Deformation , 2005, Comput. Graph. Forum.

[7]  Ghassan Hamarneh,et al.  A Survey on Shape Correspondence , 2011, Comput. Graph. Forum.

[8]  Ligang Liu,et al.  Dual Laplacian editing for meshes , 2006, IEEE Transactions on Visualization and Computer Graphics.

[9]  Lin Gao,et al.  Automatic unpaired shape deformation transfer , 2018, ACM Trans. Graph..

[10]  Sebastian Thrun,et al.  SCAPE: shape completion and animation of people , 2005, SIGGRAPH 2005.

[11]  Jovan Popović,et al.  Deformation transfer for triangle meshes , 2004, SIGGRAPH 2004.

[12]  Jovan Popović,et al.  Semantic deformation transfer , 2009, SIGGRAPH 2009.

[13]  Ghassan Hamarneh,et al.  A Survey on Shape Correspondence , 2011, Comput. Graph. Forum.

[14]  Chunxia Xiao,et al.  Dual‐domain deformation transfer for triangular meshes , 2012, Comput. Animat. Virtual Worlds.

[15]  Yinda Zhang,et al.  Neural Pose Transfer by Spatially Adaptive Instance Normalization , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  S. Mitra,et al.  Guided Deformation Transfer , 2019, European Conference on Visual Media Production.

[17]  Abd El Rahman Shabayek,et al.  Deformation transfer of 3D human shapes and poses on manifolds , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[18]  Michael J. Black,et al.  Lie Bodies: A Manifold Representation of 3D Human Shape , 2012, ECCV.

[19]  Craig Gotsman,et al.  Spatial deformation transfer , 2009, SCA '09.

[20]  Jun Saito,et al.  Smooth contact-aware facial blendshapes transfer , 2013, DigiPro.

[21]  Zheng-Jie Deng,et al.  Automatic Cage Building with Quadric Error Metrics , 2011, Journal of Computer Science and Technology.

[22]  Olga Sorkine-Hornung,et al.  Neural Cages for Detail-Preserving 3D Deformations , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Lin Gao,et al.  Fully Automatic Facial Deformation Transfer , 2020, Symmetry.

[24]  Lin Gao,et al.  Sparse Data Driven Mesh Deformation , 2017, IEEE Transactions on Visualization and Computer Graphics.

[25]  Zhigang Deng,et al.  Interactive cage generation for mesh deformation , 2017, I3D.

[26]  Lin Gao,et al.  Variational Autoencoders for Deforming 3D Mesh Models , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.