Papers › LaserMix for Semi-Supervised LiDAR Semantic Segmentation

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

30 Jun 2022CVPR 2023 1arXiv:2207.00026archive 2025-07-28

Lingdong Kong, Jiawei Ren, Liang Pan, Ziwei Liu

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised learning (SSL) in LiDAR segmentation. Our core idea is to leverage the strong spatial cues of LiDAR point clouds to better exploit unlabeled data. We propose LaserMix to mix laser beams from different LiDAR scans, and then encourage the model to make consistent and confident predictions before and after mixing. Our framework has three appealing properties: 1) Generic: LaserMix is agnostic to LiDAR representations (e.g., range view and voxel), and hence our SSL framework can be universally applied. 2) Statistically grounded: We provide a detailed analysis to theoretically explain the applicability of the proposed framework. 3) Effective: Comprehensive experimental analysis on popular LiDAR segmentation datasets (nuScenes, SemanticKITTI, and ScribbleKITTI) demonstrates our effectiveness and superiority. Notably, we achieve competitive results over fully-supervised counterparts with 2x to 5x fewer labels and improve the supervised-only baseline significantly by 10.8% on average. We hope this concise yet high-performing framework could facilitate future research in semi-supervised LiDAR segmentation. Code is publicly available.

PaperPDFConference PDFCode

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

Code

ldkong1205/LaserMix officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
yuan-zm/dgt-st mentioned on GitHubpytorchApache-2.0 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

LIDAR Semantic SegmentationSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled LaserMix (DeepLab v3+, ImageNet pre-trained ResNet50, single scale inference) Validation mIoU 77.1% #15 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled LaserMix (DeepLab v3+, ImageNet pre- trained ResNet50, single scale inference) Validation mIoU 78.3% #17 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled LaserMix (DeepLab v3+, ImageNet pre- trained ResNet50, single scale inference) Validation mIoU 79.1% #16 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Voxel) mIoU (1% Labels) 44.2 #1 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Voxel) mIoU (10% Labels) 53.7 #1 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Voxel) mIoU (20% Labels) 55.1 #1 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Voxel) mIoU (50% Labels) 56.8 #1 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Range View) mIoU (1% Labels) 38.3 #4 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Range View) mIoU (10% Labels) 54.4 #4 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Range View) mIoU (20% Labels) 55.6 #4 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI LaserMix (Range View) mIoU (50% Labels) 58.7 #4 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Voxel) mIoU (1% Labels) 50.6 #6 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Voxel) mIoU (10% Labels) 60.0 #6 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Voxel) mIoU (20% Labels) 61.9 #6 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Voxel) mIoU (50% Labels) 62.3 #6 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Range View) mIoU (1% Labels) 43.4 #8 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Range View) mIoU (10% Labels) 58.8 #8 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Range View) mIoU (20% Labels) 59.4 #8 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI LaserMix (Range View) mIoU (50% Labels) 61.4 #8 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Voxel) mIoU (1% Labels) 55.3 #3 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Voxel) mIoU (10% Labels) 69.9 #3 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Voxel) mIoU (20% Labels) 71.8 #3 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Voxel) mIoU (50% Labels) 73.2 #3 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Range View) mIoU (1% Labels) 49.5 #6 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Range View) mIoU (10% Labels) 68.2 #6 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Range View) mIoU (20% Labels) 70.6 #6 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes LaserMix (Range View) mIoU (50% Labels) 73.0 #6 of 11 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