AI RESEARCH

Poppy: Polarization-based Plug-and-Play Guidance for Enhancing Monocular Normal Estimation

arXiv CS.CV

ArXi:2603.27891v1 Announce Type: new Monocular surface normal estimators trained on large-scale RGB-normal data often perform poorly in the edge cases of reflective, textureless, and dark surfaces. Polarization encodes surface orientation independently of texture and albedo, offering a physics-based complement for these cases. Existing polarization methods, however, require multi-view capture or specialized