Papers › Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
David Bojanić, Kristijan Bartol, Josep Forest, Stefan Gumhold, Tomislav Petković, Tomislav Pribanić
Learning universal representations across different applications domain is an open research problem. In fact, finding universal architecture within the same application but across different types of datasets is still unsolved problem too, especially in applications involving processing 3D point clouds. In this work we experimentally test several state-of-the-art learning-based methods for 3D point cloud registration against the proposed non-learning baseline registration method. The proposed method either outperforms or achieves comparable results w.r.t. learning based methods. In addition, we propose a dataset on which learning based methods have a hard time to generalize. Our proposed method and dataset, along with the provided experiments, can be used in further research in studying effective solutions for universal representations. Our source code is available at: github.com/DavidBoja/greedy-grid-search.
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Point Cloud Registration | ETH (trained on 3DMatch) | Greedy Grid Search | Feature Matching Recall | 0.784 | #5 of 20 | Archive leaderboard | report |
| Point Cloud Registration | FPv1 | Greedy Grid Search | RRE (degrees) | 0.014 | #1 of 8 | Archive leaderboard | report |
| Point Cloud Registration | FPv1 | Greedy Grid Search | RTE (cm) | 0.009 | #1 of 8 | Archive leaderboard | report |
| Point Cloud Registration | FPv1 | Greedy Grid Search | Recall (3cm, 10 degrees) | 92.81 | #1 of 8 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (trained on 3DMatch) | Greedy Grid Search | Success Rate | 90.27 | #7 of 14 | 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