AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Differentiable Cloth Simulation for Inverse Problems

Junbang Liang, Ming Lin, Vladlen Koltun

NeurIPS 2019 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning · 72 citations (OpenAlex)

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 changedWhereMeasuredEffect
compute collision-response gradient via QR decomposition instead of directly solving the large linear system (ablation)differentiable cloth simulator · Backprop, 64x64 meshruntime (s): 4.6 -> 0.072Improved
compute collision-response gradient via QR decomposition (ablation)differentiable cloth simulator · Backprop, 16x16 meshruntime (s): 0.33 -> 0.013Improved
compute collision-response gradient via QR decomposition (ablation)differentiable cloth simulator · Backprop, 32x32 meshmatrix size: 1326 -> 97Improved
use analytical gradients through simulator instead of L-BFGS with finite differencecloth material estimation · Material estimationdensity error (%): 4.2 -> 1.8Improved
use analytical gradients instead of L-BFGS finite differencecloth material estimation · Material estimationsimulation error (%): 4.9 -> 1.6Improved
use analytical gradients instead of L-BFGS finite differencecloth material estimation · Material estimationbending stiffness error (%): 70 -> 77Hurt
use analytical gradients instead of L-BFGS finite differencecloth material estimation · Material estimationruntime (sec/step/iter): 2.89 -> 2.03Improved
use differentiable simulator gradients instead of PPOcloth motion control · Cloth motion controlerror (%): 432 -> 17Improved
couple simulator with a two-layer FC controller networkcloth motion control · Cloth motion controlerror (%): 17 -> 39Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy