AI RESEARCH
SEMAGIC: Learning Semantically Consistent Deformable 3D Representations from In-the-Wild Images
arXiv CS.CV
•
ArXi:2605.27938v1 Announce Type: new Learning deformable 3D object models from single-view in-the-wild images has enabled impressive 3D shape reconstruction without supervision. However, it remains unclear whether these models capture the semantic structure required for downstream tasks. We find that existing deformable reconstruction approaches, despite producing visually plausible geometry, yield unstable correspondences across instances and perform poorly on semantic correspondence benchmarks. We