Papers › CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training...
CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo
Reza Mahmoudi Kouhi, Olivier Stocker, Philippe Giguère, and Sylvie Daniel
SegContrast paved the way for contrastive learning on outdoor point clouds. Its original formulation targeted individual scans in applications like autonomous driving and object detection. However, mobile mapping purposes such as digital twin cities and urban planning require large-scale dense datasets to capture the full complexity and diversity present in outdoor environments. In this paper, the SegContrast method is revisited and adapted to overcome its limitations associated with mobile mapping datasets, namely the scarcity of contrastive pairs and memory constraints. To overcome the scarcity of contrastive pairs, we propose the merging of heterogeneous datasets. However, this merging is not a straightforward procedure due to the variety of size and number of points in the point clouds of these datasets. Therefore, a data augmentation approach is designed to create a vast number of segments while optimizing the size of the point cloud samples to the allocated memory. This methodology, called CLOUDSPAM, guarantees the performance of the self-supervised model for both small- and large-scale mobile mapping point clouds. Overall, the results demonstrate the benefits of utilizing datasets with a wide range of densities and class diversity. CLOUDSPAM matched the state of the art on the KITTI-360 dataset, with a 63.6% mIoU, and came in second place on the Toronto-3D dataset. Finally, CLOUDSPAM achieved competitive results against its fully supervised counterpart with only 10% of labeled data.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Semantic Segmentation | KITTI-360 | DA-supervised | Model size | 37.9M | #5 of 8 | Archive leaderboard | report |
| 3D Semantic Segmentation | KITTI-360 | DA-supervised | miou Val | 64.1 | #5 of 8 | Archive leaderboard | report |
| 3D Semantic Segmentation | KITTI-360 | CLOUDSPAM | Model size | 37.9M | #6 of 8 | Archive leaderboard | report |
| 3D Semantic Segmentation | KITTI-360 | CLOUDSPAM | miou Val | 63.6 | #6 of 8 | Archive leaderboard | report |
| LIDAR Semantic Segmentation | Paris-Lille-3D | CLOUDSPAM | mIOU | 0.738 | #6 of 9 | Archive leaderboard | report |
| LIDAR Semantic Segmentation | Paris-Lille-3D | DA-supervised | mIOU | 0.638 | #8 of 9 | Archive leaderboard | report |
| Semantic Segmentation | Toronto-3D L002 | CLOUDSPAM | mIoU | 71.8 | #4 of 5 | Archive leaderboard | report |
| Semantic Segmentation | Toronto-3D L002 | DA-supervised | mIoU | 69.3 | #5 of 5 | 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
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