AI RESEARCH
First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction
arXiv CS.CV
•
ArXi:2605.03463v1 Announce Type: new Neural Surface Reconstruction has become a standard methodology for indoor 3D reconstruction, with Signed Distance Functions (SDFs) proving particularly effective for representing scene geometry. A variety of applications require a detailed understanding of the scene context, driving the need for object-level semantic signals. While recent methods successfully integrate semantic labels, they often inherit the slow