Methods › Computer Vision › Point Cloud Models › PREDATOR
PREDATOR
Introduced by Shengyu Huang et al. in PREDATOR: Registration of 3D Point Clouds with Low Overlap
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
PREDATOR is a model for pairwise point-cloud registration with deep attention to the overlap region. Its key novelty is an overlap-attention block for early information exchange between the latent encodings of the two point clouds. In this way the subsequent decoding of the latent representations into per-point features is conditioned on the respective other point cloud, and thus can predict which points are not only salient, but also lie in the overlap region between the two point clouds.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Deep Models with Fusion Strategies for MVP Point Cloud Registration 18 Oct 2021 · 1 repository · arXiv:2110.09129
-
PREDATOR: Registration of 3D Point Clouds with Low Overlap 25 Nov 2020 · 5 repositories · arXiv:2011.13005Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Point Cloud Registration | 2 |
| Deep Attention | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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