Invertible Neural Skinning
Not on the map. Why?
Abstract (arXiv)
Building animatable and editable models of clothed humans from raw 3D scans and poses is a challenging problem. Existing reposing methods suffer from the limited expressiveness of Linear Blend Skinning (LBS), require costly mesh extraction to generate each new pose, and typically do not preserve surface correspondences across different poses. In this work, we introduce Invertible Neural Skinning (INS) to address these shortcomings. To maintain correspondences, we propose a Pose-conditioned Invertible Network (PIN) architecture, which extends the LBS process by learning additional pose-varying deformations. Next, we combine PIN with a differentiable LBS module to build an expressive and end-to-end Invertible Neural Skinning (INS) pipeline. We demonstrate the strong performance of our method by outperforming the state-of-the-art reposing techniques on clothed humans and preserving surface correspondences, while being an order of magnitude faster. We also perform an ablation study, which shows the usefulness of our pose-conditioning formulation, and our qualitative results display that INS can rectify artefacts introduced by LBS well. See our webpage for more details: https://yashkant.github.io/invertible-neural-skinning/
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 52 of its 71 references that are in the map. First posted on arXiv 18 Feb 2023.
Builds on
52 of 71 references.
References · 52
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2016Density estimation using Real NVPcited by 2,029
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
- 2014NICE: Non-linear Independent Components Estimationcited by 1,052
- 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
38 more
- 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
- 2017Masked Autoregressive Flow for Density Estimationcited by 680
- 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
- 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
- 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
- 2018Invertible Residual Networkscited by 364
- 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
- 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
- 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
- 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
- 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 230
- 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
- 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
- 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
- 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
- 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
- 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
- 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
- 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
- 2019NASA: Neural Articulated Shape Approximationcited by 149
- 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
- 2018i-RevNet: Deep Invertible Networkscited by 137
- 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
- 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
- 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
- 2019Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"cited by 106
- 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 102
- 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
- 2018Creatures great and SMAL: Recovering the shape and motion of animals from videocited by 84
- 2020Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loopcited by 81
- 2020Physics informed deep learning for computational elastodynamics without labeled datacited by 79
- 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
- 2022gDNA: Towards Generative Detailed Neural Avatarscited by 72
- 2022Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Cameracited by 57
- 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 56
- 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
- 2020DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modelingcited by 49
- 2021Dynamic Surface Function Networks for Clothed Human Bodiescited by 44
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.