Reproduce “RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction” 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
Zhen Li, Haoran Qin, Francesco Di Sario, Daniel Rebain, Andrea Tagliasacchi
RoboCloth builds a dataset of 500 real cloth materials using robot-controlled camera and lighting positions and a turntable for flexible view-light capture. It trains a shared BRDF decoder and fits dense material maps to new fabrics. On 12 UBO2014 materials, it averaged 36.76 dB PSNR, above Disney PBR and Bonn-trained alternatives. This supports transfer on that benchmark, not universal generalization.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.