Reproduce “Physical-Field-Bridged Material Parameter Inference from Multi-View Deformation Videos” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Linrui Shou, Jie Li, Yu Liu, Tao Huang

The authors introduce a method that estimates a deformable object’s global material type and four parameters from multi-view video. It predicts contact, motion flow, and stress fields, then feeds those fields into the estimator. On object-held-out tests, all four median absolute errors improve over direct regression; Young’s modulus error in log1p space falls from 1.901 to 1.521, though mean sample-wise error is higher.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.