RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation
Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has followed suit -- yet existing methods remain confined to object-centric perception, neglecting spatial relations between objects. We formulate 3D spatial relation segmentation...
Minsu Kim, Jaesung Choe, J. Lee et al.
· 0 citations