Reproduce “Trainspotting: Learning Object-Centric 3D Reconstruction from Found Photos” 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
Hanyu Chen, Noah Snavely
The authors introduce Trainspotting, a dataset of 12,068 objects and 311,886 found photos, and fine-tune VGGT-Ω on its varied captures to create SPOTTER. Camera AUC@30, measuring pose accuracy up to 30°, rises from 25.0 to 81.2 on held-out objects and from 18.8 to 76.0 on NAVI in-the-wild; the former uses pseudo-ground truth.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.