A feed-forward transformer estimates per-pixel normal, albedo, roughness, and metallicity from single-shot spectro-polarimetric measurements captured with a polarimetric display and augmented RGB polarization camera, using a generative manifold to expand limited BRDF training data.
Neural lightrig: Unlocking accurate object normal and material estimation with multi-light diffusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Snapshot Polarimetric Display Inverse Rendering
A feed-forward transformer estimates per-pixel normal, albedo, roughness, and metallicity from single-shot spectro-polarimetric measurements captured with a polarimetric display and augmented RGB polarization camera, using a generative manifold to expand limited BRDF training data.