L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model
Wang, Ruoyu Ma, Yukai Yao, Yi Tao, Sheng Li, Haoang Zhu, Zongzhi Liu, Yong Zuo, Xingxing
Wang, Ruoyu
Ma, Yukai
Yao, Yi
Tao, Sheng
Li, Haoang
Zhu, Zongzhi
Liu, Yong
Zuo, Xingxing
Supervisor
Department
Robotics
Embargo End Date
Type
Conference proceeding
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Semantic Scene Completion (SSC) constitutes a pivotal element in autonomous driving perception systems, tasked with inferring the 3D semantic occupancy of a scene from sensory data. To improve accuracy, prior research has implemented various computationally demanding and memory-intensive 3D operations, imposing significant computational requirements on the platform during training and testing. This paper proposes L2COcc, a lightweight camera-centric SSC framework that also accommodates LiDAR inputs. With our proposed efficient voxel transformer (EVT) and cross-modal knowledge modules, including feature similarity distillation (FSD), TPV distillation (TPVD) and prediction alignment distillation (PAD), our method substantially reduce computational burden while maintaining high accuracy. The experimental evaluations demonstrate that our proposed method surpasses the current state-of-the-art vision-based SSC methods regarding accuracy on both the SemanticKITTI and SSCBench-KITTI-360 benchmarks, respectively. Additionally, our method is more lightweight, exhibiting a reduction in both memory consumption and inference time by over 23% compared to the current state-of-the-arts method. Code is available at our project page: https://studyingfufu.github.io/L2COcc/.
Citation
R. Wang, Y. Ma, Y. Yao, S. Tao, H. Li, Z. Zhu, Y. Liu, X. Zuo, "L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model," 2025, pp. 716-723.
Source
Conference
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Keywords
40 Engineering, 46 Information and Computing Sciences, 4605 Data Management and Data Science
Subjects
Source
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)