L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model
This work addresses computational efficiency for autonomous driving perception systems, though it is incremental as it builds on existing SSC methods with distillation techniques.
The paper tackled the problem of high computational demands in Semantic Scene Completion (SSC) for autonomous driving by proposing L2COcc, a lightweight camera-centric framework that reduces memory consumption and inference time by over 23% while surpassing state-of-the-art vision-based methods in accuracy on benchmarks like SemanticKITTI and SSCBench-KITTI-360.
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/.