SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation
This addresses the challenge of real-time semantic perception in autonomous driving by improving accuracy with temporal information, though it is incremental as it builds on existing methods.
The paper tackled the problem of 4D spatio-temporal LiDAR semantic segmentation for autonomous driving by proposing SVQNet, which efficiently uses historical frames to enhance perception, achieving state-of-the-art performance on benchmarks like SemanticKITTI and nuScenes.
LiDAR-based semantic perception tasks are critical yet challenging for autonomous driving. Due to the motion of objects and static/dynamic occlusion, temporal information plays an essential role in reinforcing perception by enhancing and completing single-frame knowledge. Previous approaches either directly stack historical frames to the current frame or build a 4D spatio-temporal neighborhood using KNN, which duplicates computation and hinders realtime performance. Based on our observation that stacking all the historical points would damage performance due to a large amount of redundant and misleading information, we propose the Sparse Voxel-Adjacent Query Network (SVQNet) for 4D LiDAR semantic segmentation. To take full advantage of the historical frames high-efficiently, we shunt the historical points into two groups with reference to the current points. One is the Voxel-Adjacent Neighborhood carrying local enhancing knowledge. The other is the Historical Context completing the global knowledge. Then we propose new modules to select and extract the instructive features from the two groups. Our SVQNet achieves state-of-the-art performance in LiDAR semantic segmentation of the SemanticKITTI benchmark and the nuScenes dataset.