AI RESEARCH
Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction
arXiv CS.CV
•
ArXi:2510.04714v5 Announce Type: replace 3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations and explored various approaches including Open-Vocabulary settings, they frequently fail to optimize the representational capacity of object and relationship features, showing excessive reliance on Graph Neural Networks despite insufficient discriminative capability.