SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation

TL;DR

SVQNet introduces a novel sparse voxel-adjacent query method for efficient 4D LiDAR semantic segmentation, effectively leveraging historical data while maintaining real-time performance.

Contribution

The paper proposes SVQNet, a new framework that selectively utilizes historical LiDAR data through voxel-adjacent and global context modules, improving segmentation accuracy and efficiency.

Findings

Achieves state-of-the-art results on SemanticKITTI and nuScenes datasets.

Effectively balances information utilization and computational efficiency.

Outperforms previous methods in real-time LiDAR semantic segmentation.

Abstract

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.