Papers › PREDATOR: Registration of 3D Point Clouds with Low Overlap

PREDATOR: Registration of 3D Point Clouds with Low Overlap

25 Nov 2020CVPR 2021 1arXiv:2011.13005archive 2025-07-28

Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. 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. The ability to focus on points that are relevant for matching greatly improves performance: PREDATOR raises the rate of successful registrations by more than 20% in the low-overlap scenario, and also sets a new state of the art for the 3DMatch benchmark with 89% registration recall.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (ShengyuH/OverlapPredator) was not harvested; the 1 sample below comes from 1 community repository.

Syntology 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

By repository: community (archive-listed): 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ShengyuH/OverlapPredator officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
overlappredator/OverlapPredator mentioned on GitHubpytorchSyntology: not harvested report
prs-eth/overlappredator mentioned on GitHubpytorchSyntology: not harvested report
qinzheng93/geotransformer mentioned on GitHubpytorchMITSyntology: not harvested report
zhulf0804/predator mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified 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

1 sample harvested: 0 ran · 1 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1unverified

Licence: 1 of the 1 sample is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhulf0804/predator. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

zhulf0804/predator community (archive-listed) 1 sample, 0 ran · 1 unverified
get_scene_split evaluate.py unverified no licence file found · pointer only · c3ed06470cb387cf · report

Tasks

Deep AttentionPoint Cloud Registration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Registration 3DLoMatch (10-30% overlap) Predator-1k Recall ( correspondence RMSE below 0.2) 62.5 #5 of 13 Archive leaderboard report
Point Cloud Registration 3DLoMatch (10-30% overlap) Predator-5k Recall ( correspondence RMSE below 0.2) 59.8 #6 of 13 Archive leaderboard report
Point Cloud Registration 3DLoMatch (10-30% overlap) Predator-NR Recall ( correspondence RMSE below 0.2) 24 #12 of 13 Archive leaderboard report
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) Predator-1k Recall ( correspondence RMSE below 0.2) 90.5 #3 of 11 Archive leaderboard report
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) Predator-5k Recall ( correspondence RMSE below 0.2) 89 #4 of 11 Archive leaderboard report
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) Predator-NR Recall ( correspondence RMSE below 0.2) 62.7 #10 of 11 Archive leaderboard report
Point Cloud Registration KITTI (trained on 3DMatch) Predator Success Rate 41.20 #12 of 14 Archive leaderboard report
Point Cloud Registration RotKITTI Registration Benchmark PREDATOR RR@(1,0.1) 35.0 #4 of 6 Archive leaderboard report
Point Cloud Registration RotKITTI Registration Benchmark PREDATOR RR@(1.5,0.3) 41.6 #4 of 6 Archive leaderboard report
Point Cloud Registration ScanNet++ (trained on 3DMatch) Predator Recall ( correspondence RMSE below 0.2) 63.7 #3 of 3 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

Introduced by this paper: PREDATOR

PREDATOR

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