DetVPCC: RoI-based Point Cloud Sequence Compression for 3D Object Detection
This work addresses the challenge of balancing compression efficiency with detection accuracy in 3D object detection for autonomous driving applications, representing an incremental improvement over existing VPCC methods.
The paper tackles the problem of point cloud sequence compression for 3D object detection, where standard methods like VPCC compromise detection accuracy for bitrate savings. The proposed DetVPCC method integrates region-of-interest encoding to prioritize important regions, resulting in significantly improved detection accuracy on the nuScenes dataset.
While MPEG-standardized video-based point cloud compression (VPCC) achieves high compression efficiency for human perception, it struggles with a poor trade-off between bitrate savings and detection accuracy when supporting 3D object detectors. This limitation stems from VPCC's inability to prioritize regions of different importance within point clouds. To address this issue, we propose DetVPCC, a novel method integrating region-of-interest (RoI) encoding with VPCC for efficient point cloud sequence compression while preserving the 3D object detection accuracy. Specifically, we augment VPCC to support RoI-based compression by assigning spatially non-uniform quality levels. Then, we introduce a lightweight RoI detector to identify crucial regions that potentially contain objects. Experiments on the nuScenes dataset demonstrate that our approach significantly improves the detection accuracy. The code and demo video are available in supplementary materials.