AI RESEARCH

Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting

arXiv CS.CV

ArXi:2604.09045v1 Announce Type: new Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level 3D segmentation. However, the supervision signals from foundation models are not fundamentally object-centric and often require additional mask pre/post-processing or specialized