SplitOcc: Multi-Resolution Sparse Voxel for Efficient LiDAR-Based Semantic Scene Completion

Chaoyi Sun, Xiaze Zhang, Ziheng Ding, Ying Cheng, Zhuoyao Wang, Rui Feng

Abstract: LiDAR-based Semantic Scene Completion (SSC) is crucial for enhancing environmental perception and ensuring safety in autonomous driving. However, current methods face challenges in balancing accuracy and computational efficiency. On the one hand, projection-based methods reduce complexity but often suffer from spatial information loss. On the other hand, voxel-based methods preserve 3D structures but are computationally expensive. To address these limitations, we introduce SplitOcc, a novel multi-resolution approach that utilizes low-resolution voxels to represent large structures (e.g., road) and high-resolution voxels for detailed objects (e.g., bicycle). By employing multi-resolution sparse semantic voxels, SplitOcc can understand and represent the environment efficiently and accurately. Furthermore, the proposed Multi-Label Loss and Delayed-Drop strategies improve accuracy by preserving key semantic details during reconstruction. Extensive experiments demonstrate that our SplitOcc outperforms existing state-of-the-art methods across multiple evaluation metrics, showing notable improvements in both perception accuracy and detail preservation.

External IDs:doi:10.3233/faia250877