Research map / Probabilistic and scientific modeling / Dynamical systems
Differentiable Cloth Simulation for Inverse Problems
Junbang Liang, Ming Lin, Vladlen Koltun
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| compute collision-response gradient via QR decomposition instead of directly solving the large linear system (ablation) | differentiable cloth simulator · Backprop, 64x64 mesh | runtime (s): 4.6 -> 0.072 | Improved |
| compute collision-response gradient via QR decomposition (ablation) | differentiable cloth simulator · Backprop, 16x16 mesh | runtime (s): 0.33 -> 0.013 | Improved |
| compute collision-response gradient via QR decomposition (ablation) | differentiable cloth simulator · Backprop, 32x32 mesh | matrix size: 1326 -> 97 | Improved |
| use analytical gradients through simulator instead of L-BFGS with finite difference | cloth material estimation · Material estimation | density error (%): 4.2 -> 1.8 | Improved |
| use analytical gradients instead of L-BFGS finite difference | cloth material estimation · Material estimation | simulation error (%): 4.9 -> 1.6 | Improved |
| use analytical gradients instead of L-BFGS finite difference | cloth material estimation · Material estimation | bending stiffness error (%): 70 -> 77 | Hurt |
| use analytical gradients instead of L-BFGS finite difference | cloth material estimation · Material estimation | runtime (sec/step/iter): 2.89 -> 2.03 | Improved |
| use differentiable simulator gradients instead of PPO | cloth motion control · Cloth motion control | error (%): 432 -> 17 | Improved |
| couple simulator with a two-layer FC controller network | cloth motion control · Cloth motion control | error (%): 17 -> 39 | Hurt |
Closest papers by meaning
- NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory (NeurIPS 2024 · similarity 0.89)
- SENC: Handling Self-collision in Neural Cloth Simulation (ECCV 2024 · similarity 0.88)
- NeuralGarSim: Geometry-agnostic Garment Simulation with Neural Fields (ECCV 2026 · similarity 0.88)
- Bayesian Differentiable Physics for Cloth Digitalization (CVPR 2024 · similarity 0.88)
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.87)
- GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
