RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision

• Published in: arXiv.org
• Main Authors: Pan, Mingjie, Liu, Jiaming, Zhang, Renrui, Huang, Peixiang, Li, Xiaoqi, Wang, Bing, Xie, Hongwei, Liu, Li, Zhang, Shanghang
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 04.03.2024
• Subjects: Annotations; Labels; Rendering; Semantics; Supervision; Three dimensional models

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel space for supervision. However, the expensive annotation proc...