Reproduce “Photometric Mesh Optimization for Video-Aligned 3D Object 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
Chen-Hsuan Lin, Oliver Wang, Bryan C. Russell, Eli Shechtman, Vladimir G. Kim, Matthew Fisher, Simon Lucey
The method refines an image-encoder-initialized AtlasNet mesh against photometric evidence across RGB video frames, updating its latent shape code. It compares visible mesh-face samples through a shared virtual viewpoint without depth or masks as optimization cues. On 13 ShapeNet categories, mean shape-accuracy error is 2.163 versus 4.723 for AtlasNet mean shape; real-world use still requires camera estimation and coarse alignment.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.