mlsanityData to 14 Oct 2026

A Repulsive Force Unit for Garment Collision Handling in Neural Networks

arXiv 2207.13871 ↗First posted 28 Jul 2022cs.GR cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Despite recent success, deep learning-based methods for predicting 3D garment deformation under body motion suffer from interpenetration problems between the garment and the body. To address this problem, we propose a novel collision handling neural network layer called Repulsive Force Unit (ReFU). Based on the signed distance function (SDF) of the underlying body and the current garment vertex positions, ReFU predicts the per-vertex offsets that push any interpenetrating vertex to a collision-free configuration while preserving the fine geometric details. We show that ReFU is differentiable with trainable parameters and can be integrated into different network backbones that predict 3D garment deformations. Our experiments show that ReFU significantly reduces the number of collisions between the body and the garment and better preserves geometric details compared to prior methods based on collision loss or post-processing optimization.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 22 of its 49 references that are in the map. First posted on arXiv 28 Jul 2022.

Builds on

22 of 49 references.

References · 22

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  4. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  5. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  6. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  7. 2019NASA: Neural Articulated Shape Approximationcited by 149
  8. 2020TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Stylecited by 149
  9. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  10. 2019CLOTH3D: Clothed 3D Humanscited by 116
  11. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  12. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 103
10 more
  1. 2019Learning-Based Animation of Clothing for Virtual Try-Oncited by 89
  2. 2021Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-Oncited by 81
  3. 2018GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Drapingcited by 69
  4. 2020PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformationcited by 63
  5. 2020Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernelscited by 53
  6. 2018Learning a Shared Shape Space for Multimodal Garment Designcited by 52
  7. 2020DeePSD: Automatic Deep Skinning And Pose Space Deformation For 3D Garment Animationcited by 43
  8. 2019Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embeddingcited by 9
  9. 2020LCollision: Fast Generation of Collision-Free Human Poses using Learned Non-Penetration Constraintscited by 8
  10. 2021Active Learning of Neural Collision Handler for Complex 3D Mesh Deformationscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 3.

7 papers.

  1. 2023Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Inputcited by 22
  2. 2024SENC: Handling Self-collision in Neural Cloth Simulationcited by 4
  3. 2023SwinGar: Spectrum-Inspired Neural Dynamic Deformation for Free-Swinging Garmentscited by 3
  4. 2026ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulationcited by 3
  5. 2024Shallow Signed Distance Functions for Kinematic Collision Bodiescited by 0
  6. 2026PhysDrape: Learning Explicit Forces and Collision Constraints for Physically Realistic Garment Drapingcited by 0
  7. 2026PoseShield: Neural Collision Fields for Human Self-Collision Resolutioncited by 0