GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding

arXiv:2311.11863v2 Announce Type: replace
Abstract: Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering" task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception …

abstract arxiv build context cs.cv generalized however instance labels nerf per perception pixel popular prediction rendering representation semantic tasks type understanding