Papers › 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds

10 Jul 2022arXiv:2207.04397archive 2025-07-28

Xu Yan, Jiantao Gao, Chaoda Zheng, Chao Zheng, Ruimao Zhang, Shenghui Cui, Zhen Li

As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion. However, fusion-based approaches require paired data, i.e., LiDAR point clouds and camera images with strict point-to-pixel mappings, as the inputs in both training and inference, which seriously hinders their application in practical scenarios. Thus, in this work, we propose the 2D Priors Assisted Semantic Segmentation (2DPASS), a general training scheme, to boost the representation learning on point clouds, by fully taking advantage of 2D images with rich appearance. In practice, by leveraging an auxiliary modal fusion and multi-scale fusion-to-single knowledge distillation (MSFSKD), 2DPASS acquires richer semantic and structural information from the multi-modal data, which are then online distilled to the pure 3D network. As a result, equipped with 2DPASS, our baseline shows significant improvement with only point cloud inputs. Specifically, it achieves the state-of-the-arts on two large-scale benchmarks (i.e. SemanticKITTI and NuScenes), including top-1 results in both single and multiple scan(s) competitions of SemanticKITTI.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

yanx27/2dpass officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Benchmarking the Robustness of LiDAR Semantic Segmentation Models (arXiv:2301.00970; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

3D Semantic SegmentationAutonomous DrivingKnowledge DistillationLIDAR Semantic SegmentationRepresentation LearningRobust 3D Semantic SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Segmentation SemanticKITTI 2DPASS test mIoU 72.9% #8 of 45 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI 2DPASS val mIoU 69.3% #8 of 45 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes 2DPASS test mIoU 0.81 #7 of 36 Archive leaderboard report
Robust 3D Semantic Segmentation SemanticKITTI-C 2DPASS mean Corruption Error (mCE) 106.14% #11 of 22 Archive leaderboard report
Robust 3D Semantic Segmentation nuScenes-C 2DPASS mean Corruption Error (mCE) 98.56% #4 of 12 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.

Methods

Knowledge Distillation

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