Papers › Unsupervised Point Cloud Pre-Training via Occlusion Completion

Unsupervised Point Cloud Pre-Training via Occlusion Completion

2 Oct 2020ICCV 2021 10arXiv:2010.01089archive 2025-07-28

Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matthew J. Kusner

We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct the occluded points; 3. Use the encoder weights as initialisation for downstream point cloud tasks. We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks. Specifically, we show that our method outperforms previous pre-training methods in object classification, and both part-based and semantic segmentation tasks. We study the pre-trained features and find that they lead to wide downstream minima, have high transformation invariance, and have activations that are highly correlated with part labels. Code and data are available at: https://github.com/hansen7/OcCo

PaperPDFConference PDFCode

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

Code

hansen7/OcCo 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 Point Cloud Linear ClassificationDecoderFew-Shot 3D Point Cloud ClassificationPoint Cloud ClassificationPoint Cloud Pre-trainingPoint Cloud SegmentationSemantic SegmentationUnsupervised 3D Point Cloud Linear Evaluation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Linear Classification ModelNet40 OcCo Overall Accuracy 89.2 #16 of 20 Archive leaderboard report
3D Point Cloud Linear Classification ScanObjectNN OcCo Overall Accuracy 78.3 #4 of 4 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) OcCo+PointNet Overall Accuracy 83.9 #20 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) OcCo+PointNet Standard Deviation 1.8 #20 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) OcCo+DGCNN Overall Accuracy 82.9 #21 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) OcCo+DGCNN Standard Deviation 1.3 #21 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) OcCo+PointNet Overall Accuracy 89.7 #20 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) OcCo+PointNet Standard Deviation 1.5 #20 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) OcCo+DGCNN Overall Accuracy 86.5 #21 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) OcCo+DGCNN Standard Deviation 2.2 #21 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) OcCo+DGCNN Overall Accuracy 90.6 #19 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) OcCo+DGCNN Standard Deviation 2.8 #19 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) OcCo+PointNet Overall Accuracy 89.7 #20 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) OcCo+PointNet Standard Deviation 1.9 #20 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) OcCo+DGCNN Overall Accuracy 92.5 #19 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) OcCo+DGCNN Standard Deviation 1.9 #19 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) OcCo+PointNet Overall Accuracy 92.4 #20 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) OcCo+PointNet Standard Deviation 1.6 #20 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ScanObjectNN 10-way (10-shot) OcCo Overall Accuracy 57.0 #3 of 3 Archive leaderboard report
Point Cloud Classification PointCloud-C OcCo-DGCNN mean Corruption Error (mCE) 1.047 #20 of 24 Archive leaderboard report
Point Cloud Segmentation PointCloud-C OcCo-DGCNN mean Corruption Error (mCE) 0.977 #5 of 11 Archive leaderboard report
Point Cloud Segmentation PointCloud-C OcCo-PointNet mean Corruption Error (mCE) 1.130 #9 of 11 Archive leaderboard report
Point Cloud Segmentation PointCloud-C OcCo-PCN mean Corruption Error (mCE) 1.173 #10 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