Papers › Lepard: Learning partial point cloud matching in rigid and deformable scenes

Lepard: Learning partial point cloud matching in rigid and deformable scenes

24 Nov 2021CVPR 2022 1arXiv:2111.12591archive 2025-07-28

Yang Li, Tatsuya Harada

We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An architecture that disentangles point cloud representation into feature space and 3D position space. 2) A position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors. 3) A repositioning technique that modifies the crosspoint-cloud relative positions. Ablation studies demonstrate the effectiveness of the above techniques. In rigid cases, Lepard combined with RANSAC and ICP demonstrates state-of-the-art registration recall of 93.9% / 71.3% on the 3DMatch / 3DLoMatch. In deformable cases, Lepard achieves +27.1% / +34.8% higher non-rigid feature matching recall than the prior art on our newly constructed 4DMatch / 4DLoMatch benchmark.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2111.12591")

Code

Syntology Ran 5 of 14 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

rabbityl/lepard 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

14 samples harvested; 5 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · fixture could not drive it
3ran
9unverified

Licence: 0 of the 14 samples are 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 rabbityl/lepard. “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 “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

closest_pool rabbityl/lepard/models/blocks.py official repository ran MIT (permissive) · 728888ce9772c062 · report
gather rabbityl/lepard/models/blocks.py official repository ran · fixture could not drive it MIT (permissive) · 06eb9b038422a6ef · report
parse_header rabbityl/lepard/lib/ply.py official repository ran MIT (permissive) · 27aa4c3bde697bf7 · report
parse_mesh_header rabbityl/lepard/lib/ply.py official repository ran MIT (permissive) · 5f8cf95da4e4af73 · report
radius_gaussian rabbityl/lepard/models/blocks.py official repository ran · violated contract MIT (permissive) · 42f2cd40ba483d3b · report
blend_anchor_motion rabbityl/lepard/lib/tester.py official repository unverified MIT (permissive) · 8dabd695d63c852e · report
compute_nrfmr rabbityl/lepard/lib/tester.py official repository unverified MIT (permissive) · fb52a52876a91529 · report
fmr_wrt_distance rabbityl/lepard/lib/benchmark_utils.py official repository unverified MIT (permissive) · ae53388c0ec8e5ce · report
fmr_wrt_inlier_ratio rabbityl/lepard/lib/benchmark_utils.py official repository unverified MIT (permissive) · c1370925c2a2e2dd · report
load_config rabbityl/lepard/lib/utils.py official repository unverified MIT (permissive) · ffd2e720a55ad59b · report
load_obj rabbityl/lepard/lib/utils.py official repository unverified MIT (permissive) · 6fe44061f3a9f5f6 · report
read_ply rabbityl/lepard/lib/ply.py official repository unverified MIT (permissive) · b6122b5ef2c0c4e9 · report
square_distance rabbityl/lepard/lib/utils.py official repository unverified MIT (permissive) · 91e28be6398ac875 · report
to_tensor rabbityl/lepard/lib/benchmark_utils.py official repository unverified MIT (permissive) · d3a852d18b17ae7b · report

Tasks

3D Feature Matching3D Point Cloud MatchingPartial Point Cloud MatchingPoint Cloud Registration

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

4DMatch

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Partial Point Cloud Matching 4DMatch Li and Harada (θc=0.05) IR 80.9 #1 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Li and Harada (θc=0.05) NFMR 83.9 #1 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Li and Harada (θc=0.1) IR 82.7 #2 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Li and Harada (θc=0.1) NFMR 83.7 #2 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Li and Harada (θc=0.2) IR 85.4 #3 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Li and Harada (θc=0.2) NFMR 82.2 #3 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Predator (5000) IR 59.3 #4 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Predator (5000) NFMR 56.8 #4 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Predator (3000) IR 60.4 #5 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Predator (3000) NFMR 56.4 #5 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch D3Feat (5000) IR 55.3 #6 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch D3Feat (5000) NFMR 56.1 #6 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch D3Feat (3000) IR 54.7 #7 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch D3Feat (3000) NFMR 55.5 #7 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Predator (1000) IR 60 #8 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch Predator (1000) NFMR 53.3 #8 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch D3Feat (1000) IR 52.7 #9 of 9 Archive leaderboard report
Partial Point Cloud Matching 4DMatch D3Feat (1000) NFMR 51.6 #9 of 9 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