Filters








14,256 Hits in 1.7 sec

Semantic deformation transfer

Ilya Baran, Daniel Vlasic, Eitan Grinspun, Jovan Popović
2009 ACM SIGGRAPH 2009 papers on - SIGGRAPH '09  
Semantic deformation transfer accomplishes this task with a shape space that enables interpolation and projection with standard linear algebra.  ...  Given several example mesh pairs, semantic deformation transfer infers a correspondence between the shape spaces of the two characters. This enables automatic transfer of new poses and animations.  ...  a few example poses enable semantic deformation transfer, can we perform semantic motion transfer using example motion clips?  ... 
doi:10.1145/1576246.1531342 fatcat:ik4pkqqm7jc4hnzt5gda4g45ou

Semantic deformation transfer

Ilya Baran, Daniel Vlasic, Eitan Grinspun, Jovan Popović
2009 ACM Transactions on Graphics  
Semantic deformation transfer accomplishes this task with a shape space that enables interpolation and projection with standard linear algebra.  ...  Given several example mesh pairs, semantic deformation transfer infers a correspondence between the shape spaces of the two characters. This enables automatic transfer of new poses and animations.  ...  a few example poses enable semantic deformation transfer, can we perform semantic motion transfer using example motion clips?  ... 
doi:10.1145/1531326.1531342 fatcat:hzmdejtxk5ebrosgflcglu36sm

Human Pose Transfer by Adaptive Hierarchical Deformation [article]

Jinsong Zhang, Xingzi Liu, Kun Li
2020 arXiv   pre-print
In this paper, we propose an adaptive human pose transfer network with two hierarchical deformation levels.  ...  The first level generates human semantic parsing aligned with the target pose, and the second level generates the final textured person image in the target pose with the semantic guidance.  ...  Feature-wise Gating Our Approach As shown in Figure 2 , we propose a semantic-guided human pose transfer network with two hierarchical deformation levels.  ... 
arXiv:2012.06940v1 fatcat:v5tiht5l3jhm5hofpake7e25wm

Automatic unpaired shape deformation transfer

Lin Gao, Jie Yang, Yi-Ling Qiao, Yu-Kun Lai, Paul L. Rosin, Weiwei Xu, Shihong Xia
2018 ACM Transactions on Graphics  
First row: source fit person shapes, second row: our results of deformation transfer to a fat person.  ...  Deformation transfer from a fit person to a fat person, both from the MPI DYNA dataset [Pons-Moll et al. 2015] .  ...  First row: source face shapes, second row: semantic deformation transfer [Baran et al. 2009 ], third row: our results of deformation transfer to a person.  ... 
doi:10.1145/3272127.3275028 fatcat:t47xpxmjvbefpngzjsklkodk6u

Deformation transfer for triangle meshes

Robert W. Sumner, Jovan Popović
2004 ACM SIGGRAPH 2004 Papers on - SIGGRAPH '04  
Transfer for Triangle Meshes a Source deformed Target deformed Deformation Transfer  ...  • Transfer the deformations to the target: • Reuse of deformations which were probably created with a lot of effort Deformation TransferDeformation Transfer is purely mesh-based • No need for an  ... 
doi:10.1145/1186562.1015736 fatcat:xlpxntwbpffanokl3f3rpf76sm

Learning to Infer Semantic Parameters for 3D Shape Editing [article]

Fangyin Wei, Elena Sizikova, Avneesh Sud, Szymon Rusinkiewicz, Thomas Funkhouser
2020 arXiv   pre-print
At testing time, edits within the parameter space drive deformations to be applied to the original shape, which provides semantically-meaningful manipulation while preserving the details.  ...  We propose to learn a deep network that infers the semantic parameters of an input shape and then allows the user to manipulate those parameters.  ...  Deformation Transfer To tackle the challenge of detail preservation while performing the editing, we transfer the deformation defined by synthetic shapes to realistic shapes that are semantically close  ... 
arXiv:2011.04755v1 fatcat:mgqznmzan5dj3dq5xjpp7mntri

Example-based facial rigging

Hao Li, Thibaut Weise, Mark Pauly
2010 ACM SIGGRAPH 2010 papers on - SIGGRAPH '10  
Our system transfers controller semantics and expression dynamics from a generic template to the target blendshape model, while solving for an optimal reproduction of the training poses.  ...  EPFL training example no training with training training example no training with training whistle evil laugh smile surprise prior prior Figure 1: Example-based facial rigging allows transferring expressions  ...  Without training data, the reconstructed blendshapes correspond to pure deformation transfer.  ... 
doi:10.1145/1833349.1778769 fatcat:7wz3bip7ineiljqz6t3lmhvngi

Example-based facial rigging

Hao Li, Thibaut Weise, Mark Pauly
2010 ACM Transactions on Graphics  
Our system transfers controller semantics and expression dynamics from a generic template to the target blendshape model, while solving for an optimal reproduction of the training poses.  ...  EPFL training example no training with training training example no training with training whistle evil laugh smile surprise prior prior Figure 1: Example-based facial rigging allows transferring expressions  ...  Without training data, the reconstructed blendshapes correspond to pure deformation transfer.  ... 
doi:10.1145/1833351.1778769 fatcat:5nhhxgs5orb4bmmbba42pbnjqi

Example-based facial rigging

Hao Li, Thibaut Weise, Mark Pauly
2010 ACM Transactions on Graphics  
Our system transfers controller semantics and expression dynamics from a generic template to the target blendshape model, while solving for an optimal reproduction of the training poses.  ...  EPFL training example no training with training training example no training with training whistle evil laugh smile surprise prior prior Figure 1: Example-based facial rigging allows transferring expressions  ...  Without training data, the reconstructed blendshapes correspond to pure deformation transfer.  ... 
doi:10.1145/1778765.1778769 fatcat:zwozozp7abcpdfkx34t5pnzgle

3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations [article]

Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, Sanja Fidler
2021 arXiv   pre-print
In addition, the texture style of the target is transferred to the warped source object with the help of a multi-view differentiable renderer.  ...  Second, we jointly optimize our geometric style network and a pre-trained image style transfer network with losses defined over both the geometry and the rendering of the result.  ...  The human cartoon style transfer results show that our method does a better job in semantic-ware style transfer than baseline.  ... 
arXiv:2108.12958v1 fatcat:lnq2c53surclrnnhm2bofoe7ou

Unsupervised Person Image Generation with Semantic Parsing Transformation [article]

Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei
2019 arXiv   pre-print
Firstly, a semantic generative network is proposed to transform between semantic parsing maps, in order to simplify the non-rigid deformation learning.  ...  Our method is generalizable to other semantic-aware person image generation tasks, eg, clothing texture transfer and controlled image manipulation.  ...  The semantic generative network is trained to model the spatial semantic deformation under different poses.  ... 
arXiv:1904.03379v2 fatcat:gvw4h2psvrbsthvimimninsqeq

Learning Category-Specific Mesh Reconstruction from Image Collections [chapter]

Angjoo Kanazawa, Shubham Tulsiani, Alexei A. Efros, Jitendra Malik
2018 Lecture Notes in Computer Science  
Additionally, we show that semantic keypoints can be easily associated with the predicted shapes.  ...  The shape is represented as a deformable 3D mesh model of an object category where a shape is parameterized by a learned mean shape and per-instance predicted deformation.  ...  We also show we capture the shape deformation space of the category and that the implicit correspondences in the deformable model allow us to have applications like texture transfer across instances.  ... 
doi:10.1007/978-3-030-01267-0_23 fatcat:p3yaq7ctdbh4zfrpwjtlo23caq

Harmonic Guidance for Surface Deformation

Rhaleb Zayer, Christian Rössl, Zachi Karni, Hans-Peter Seidel
2005 Computer graphics forum (Print)  
As a general tool for both scenarios, a harmonic field is constructed to guide the interpolation of constraints and to find correspondence required for deformation transfer.  ...  , or, deformation of a reference surface is mimicked.  ...  Conclusions We presented a surface deformation framework for shape editing and deformation transfer.  ... 
doi:10.1111/j.1467-8659.2005.00885.x fatcat:bsyyfkevbjgqtpyhedqxdnoyaa

Facial Expression Retargeting from Human to Avatar Made Easy [article]

Juyong Zhang, Keyu Chen, Jianmin Zheng
2020 arXiv   pre-print
In this paper, we propose a brand-new solution to this cross-domain expression transfer problem via nonlinear expression embedding and expression domain translation.  ...  Deformation Transfer Deformation transfer (DT) [7] uses the deformation gradient to transfer the source deformation to a target.  ...  Semantic correspondence construction. Given a human model as the reference, we first generate an initial avatar using Deformation Transfer [7] .  ... 
arXiv:2008.05110v1 fatcat:nt5cq5ygbfhazkqx3sylcfljmi

"Edutainment 2017" a visual and semantic representation of 3D face model for reshaping face in images

Jiang Du, Dan Song, Yanlong Tang, Ruofeng Tong, Min Tang
2018 Journal of Visualization  
The semantic (local) bases correspond to each individual face part and they are used to semantically edit each face part, while the non-semantic bases explain other shape variations to span the subspace  ...  Second, to define the semantic bases, we train a regression model to correlate semantically significant values like nose height and mouth width.  ...  When transferring the expression between images, unlike Vlasic et al. (2005) who directly transferred the parameters of source face image to the target image, Thies et al. (2016) used a subspace deformation  ... 
doi:10.1007/s12650-018-0476-4 fatcat:mzyz3aopbbehjhzascgs5gyx3q
« Previous Showing results 1 — 15 out of 14,256 results