Papers › Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

18 Aug 2023CVPR 2024 1arXiv:2308.09718archive 2025-07-28

Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao

The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of large-scale 3D datasets. Merging multiple available data sources and letting them collaboratively train a single model is a potential solution. However, due to the large domain gap between 3D point cloud datasets, such mixed supervision could adversely affect the model's performance and lead to degenerated performance (i.e., negative transfer) compared to single-dataset training. In view of this challenge, we introduce Point Prompt Training (PPT), a novel framework for multi-dataset synergistic learning in the context of 3D representation learning that supports multiple pre-training paradigms. Based on this framework, we propose Prompt-driven Normalization, which adapts the model to different datasets with domain-specific prompts and Language-guided Categorical Alignment that decently unifies the multiple-dataset label spaces by leveraging the relationship between label text. Extensive experiments verify that PPT can overcome the negative transfer associated with synergistic learning and produce generalizable representations. Notably, it achieves state-of-the-art performance on each dataset using a single weight-shared model with supervised multi-dataset training. Moreover, when served as a pre-training framework, it outperforms other pre-training approaches regarding representation quality and attains remarkable state-of-the-art performance across over ten diverse downstream tasks spanning both indoor and outdoor 3D scenarios.

PaperPDFConference PDFCode

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

Code

Pointcept/Pointcept officialmentioned in papermentioned on GitHubpytorchMIT 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 SegmentationLIDAR Semantic SegmentationRepresentation LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Segmentation ScanNet200 PPT+SparseUNet test mIoU 33.2 #12 of 16 Archive leaderboard report
3D Semantic Segmentation ScanNet200 PPT+SparseUNet val mIoU 31.9 #12 of 16 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI PPT+SparseUNet val mIoU 71.4% #42 of 45 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes PPT+SparseUNet val mIoU 0.786 #35 of 36 Archive leaderboard report
Semantic Segmentation S3DIS PPT + SparseUNet Mean IoU 78.1 #6 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PPT + SparseUNet Number of params N/A #6 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PPT + SparseUNet mAcc 85.4 #6 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PPT + SparseUNet oAcc 92.2 #6 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PPT + SparseUNet Number of params N/A #16 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PPT + SparseUNet mAcc 78.2 #16 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PPT + SparseUNet mIoU 72.7 #16 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PPT + SparseUNet oAcc 91.5 #16 of 61 Archive leaderboard report
Semantic Segmentation ScanNet PPT + SparseUNet test mIoU 76.6 #12 of 45 Archive leaderboard report
Semantic Segmentation ScanNet PPT + SparseUNet val mIoU 76.4 #12 of 45 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