mlsanityData to 14 Oct 2026

Patch-based Representation and Learning for Efficient Deformation Modeling

arXiv 2601.05035 ↗First posted 8 Jan 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a patch-based representation of surfaces, PolyFit, which is obtained by fitting jet functions locally on surface patches. Such a representation can be learned efficiently in a supervised fashion from both analytic functions and real data. Once learned, it can be generalized to various types of surfaces. Using PolyFit, the surfaces can be efficiently deformed by updating a compact set of jet coefficients rather than optimizing per-vertex degrees of freedom for many downstream tasks in computer vision and graphics. We demonstrate the capabilities of our proposed methodologies with two applications: 1) Shape-from-template (SfT): where the goal is to deform the input 3D template of an object as seen in image/video. Using PolyFit, we adopt test-time optimization that delivers competitive accuracy while being markedly faster than offline physics-based solvers, and outperforms recent physics-guided neural simulators in accuracy at modest additional runtime. 2) Garment draping. We train a self-supervised, mesh- and garment-agnostic model that generalizes across resolutions and garment types, delivering up to an order-of-magnitude faster inference than strong baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 80 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

36 of 80 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  4. 2015Spatial Transformer Networkscited by 1,429
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  7. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  8. 2020TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Stylecited by 149
  9. 2019CLOTH3D: Clothed 3D Humanscited by 116
  10. 2018ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Roboticscited by 98
  11. 2018DeepWrinkles: Accurate and Realistic Clothing Modelingcited by 90
  12. 2019Learning-Based Animation of Clothing for Virtual Try-Oncited by 89
24 more
  1. 2022SNUG: Self-Supervised Neural Dynamic Garmentscited by 83
  2. 2021Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-Oncited by 81
  3. 2022HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamicscited by 78
  4. 2021DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contactcited by 65
  5. 2020PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformationcited by 63
  6. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
  7. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
  8. 2020Fully Convolutional Graph Neural Networks for Parametric Virtual Try-Oncited by 48
  9. 2020DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squarescited by 43
  10. 2022Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networkscited by 39
  11. 2019DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequencescited by 37
  12. 2019Shape Reconstruction by Learning Differentiable Surface Representationscited by 37
  13. 2022Neural Cloth Simulationcited by 36
  14. 2022Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshescited by 28
  15. 2021Dynamic Neural Garmentscited by 27
  16. 2020GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Losscited by 24
  17. 2020Better Patch Stitching for Parametric Surface Reconstructioncited by 21
  18. 2019IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstructioncited by 16
  19. 2023Towards Multi-Layered 3D Garments Animationcited by 16
  20. 2018HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Modelcited by 15
  21. 2018Geometry-Aware Network for Non-Rigid Shape Prediction from a Single Viewcited by 15
  22. 2023GAPS: Geometry-Aware, Physics-Based, Self-Supervised Neural Garment Drapingcited by 9
  23. 2023Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Modelscited by 8
  24. 2023ROBUSfT: Robust Real-Time Shape-from-Template, a C++ Librarycited by 6

Built on by

Not cited yet.