← Search

Krispin Wandel

1 accepted papers

2025

SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations

CVPR 2025poster

Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics, the same can currently not be said for capturing global geometric relationships between semantic object regions. This p…

Cited by 0SourcePDFScholar