Sparse Cross-Scale Attention Network for Efficient LiDAR Panoptic Segmentation
Shuangjie Xu, Rui Wan, Maosheng Ye, Xiaoyi Zou, Tongyi Cao
[AAAI-22] Main Track
Abstract:
Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that point clouds of an object are surface-aggregated and thus hard to model the long-range dependency especially for large instances, and that objects are too close to separate each other. Recent literature addresses these problems by time-consuming grouping processes such as dual-clustering, mean-shift offsets and etc., or by bird-eye-view (BEV) dense centroid representation that downplays geometry. However, the long-range geometry relationship has not been sufficiently modeled by local feature learning from the above methods. To this end, we present SCAN, a novel sparse cross-scale attention network to first align multi-scale sparse features with global voxel-encoded attention to capture the long-range relationship of instance context, which is able to boost the regression accuracy of the over-segmented large objects. For the surface-aggregated points, SCAN adopts a novel sparse class-agnostic representation of instance centroids, which can not only maintain the sparsity of aligned features to solve the under-segmentation on small objects, but also reduce the computation amount of the network through sparse convolution. Our method outperforms previous methods by a large margin in the SemanticKITTI dataset for the challenging 3D PS task, achieving 1st place with a real-time inference speed.
Introduction Video
Sessions where this paper appears
-
Poster Session 6
Sat, February 26 8:45 AM - 10:30 AM (+00:00)
Red 3
-
Poster Session 10
Sun, February 27 4:45 PM - 6:30 PM (+00:00)
Red 3
-
Oral Session 10
Sun, February 27 6:30 PM - 7:45 PM (+00:00)
Red 3