Papers › Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape...

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

7 Dec 2020arXiv:2012.03762archive 2025-07-28

Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yanx27/JS3C-Net officialmentioned in papermentioned on GitHubpytorch report
umich-curly/3dmapping mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Semantic Scene Completion3D Semantic Scene Completion from a single RGB image3D Semantic SegmentationAutonomous DrivingPoint Cloud SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Scene Completion SemanticKITTI JS3C-Net mIoU 23.8 #4 of 20 Archive leaderboard report
3D Semantic Scene Completion from a single RGB image SemanticKITTI JS3C-Net (rgb input - reported in MonoScene paper) mIoU 8.97 #7 of 9 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI JS3C-Net test mIoU 66.0% #15 of 45 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes JS3C-Net test mIoU 0.74 #23 of 36 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections