Geometric Inconsistency Localization in Multi-View Image Sets
DeformView is introduced, a wide-baseline MV dataset with pixel-level annotations of geometric inconsistencies and DEFECt3R is proposed, a lightweight learning-based classifier that uses cross-view feature relationships to localize geometric inconsistencies at the pixel level.
Xander Staelens, Albéric Loos, Bert Ramlot et al.
· 0 citations