Papers › Position-Guided Point Cloud Panoptic Segmentation Transformer

Position-Guided Point Cloud Panoptic Segmentation Transformer

23 Mar 2023arXiv:2303.13509archive 2025-07-28

Zeqi Xiao, Wenwei Zhang, Tai Wang, Chen Change Loy, Dahua Lin, Jiangmiao Pang

DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception. This work begins by applying this appealing paradigm to LiDAR-based point cloud segmentation and obtains a simple yet effective baseline. Although the naive adaptation obtains fair results, the instance segmentation performance is noticeably inferior to previous works. By diving into the details, we observe that instances in the sparse point clouds are relatively small to the whole scene and often have similar geometry but lack distinctive appearance for segmentation, which are rare in the image domain. Considering instances in 3D are more featured by their positional information, we emphasize their roles during the modeling and design a robust Mixed-parameterized Positional Embedding (MPE) to guide the segmentation process. It is embedded into backbone features and later guides the mask prediction and query update processes iteratively, leading to Position-Aware Segmentation (PA-Seg) and Masked Focal Attention (MFA). All these designs impel the queries to attend to specific regions and identify various instances. The method, named Position-guided Point cloud Panoptic segmentation transFormer (P3Former), outperforms previous state-of-the-art methods by 3.4% and 1.2% PQ on SemanticKITTI and nuScenes benchmark, respectively. The source code and models are available at https://github.com/SmartBot-PJLab/P3Former .

PaperPDFCode

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

Code

smartbot-pjlab/p3former officialmentioned in papermentioned 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

Instance SegmentationPanoptic SegmentationPoint Cloud SegmentationSegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation SemanticKITTI P3Former PQ 0.649 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former PQ_dagger 0.7 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former PQst 0.633 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former PQth 0.671 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former RQ 0.759 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former RQst 0.772 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former RQth 0.741 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former SQ 0.849 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former SQst 0.807 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former SQth 0.906 #1 of 2 Archive leaderboard report
Panoptic Segmentation SemanticKITTI P3Former mIoU 0.683 #1 of 2 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