Papers › PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

13 Mar 2019CVPR 2019 6arXiv:1903.05711archive 2025-07-28

Yasuhiro Aoki, Hunter Goforth, Rangaprasad Arun Srivatsan, Simon Lucey

PointNet has revolutionized how we think about representing point clouds. For classification and segmentation tasks, the approach and its subsequent extensions are state-of-the-art. To date, the successful application of PointNet to point cloud registration has remained elusive. In this paper we argue that PointNet itself can be thought of as a learnable "imaging" function. As a consequence, classical vision algorithms for image alignment can be applied on the problem - namely the Lucas & Kanade (LK) algorithm. Our central innovations stem from: (i) how to modify the LK algorithm to accommodate the PointNet imaging function, and (ii) unrolling PointNet and the LK algorithm into a single trainable recurrent deep neural network. We describe the architecture, and compare its performance against state-of-the-art in common registration scenarios. The architecture offers some remarkable properties including: generalization across shape categories and computational efficiency - opening up new paths of exploration for the application of deep learning to point cloud registration. Code and videos are available at https://github.com/hmgoforth/PointNetLK.

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="1903.05711")

Code

Syntology Ran 2 of 24 code samples harvested from 2 repositories linked to this paper; 22 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 2 samples from 1 repository, 2 ran; community (archive-listed): 22 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hmgoforth/PointNetLK officialmentioned in paperpytorch report
izhangrui/paper_to_read mentioned on GitHub report
julians89/PointNetLK-Tensorflow mentioned on GitHubtf report
vinits5/PointNetLK mentioned on GitHubpytorchMIT report
vinits5/learning3d mentioned on GitHubpytorch 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

24 samples harvested; 2 ran; 0 honoured the contract we drafted; 22 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.

2ran · our draft was wrong
22unverified

Licence: 22 of the 24 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

options hmgoforth/PointNetLK/experiments/train_pointlk.py official repository ran · our draft was wrong MIT (permissive) · 91b0d9f4e103224c · report
options hmgoforth/PointNetLK/experiments/test_pointlk.py official repository ran · our draft was wrong MIT (permissive) · 6a47d24a9770c899 · report
batch_inverse vinits5/PointNetLK/utils/invmat.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 62e0a53461028a1f · report
batch_inverse_dx vinits5/PointNetLK/utils/invmat.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 4fbdd532c7b1a6d6 · report
batch_pinv_dx vinits5/PointNetLK/utils/invmat.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · d764d841ff3bb5c9 · report
classes_to_cinfo vinits5/PointNetLK/utils/globset.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · a5c9a61008665ff1 · report
cross_prod vinits5/PointNetLK/utils/so3.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · bb80e2d7df517e02 · report
find_classes vinits5/PointNetLK/utils/globset.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 5d874cf35d01bf68 · report
flatten vinits5/PointNetLK/model.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · aaa5e6d5223ca869 · report
glob_dataset vinits5/PointNetLK/utils/globset.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · dd50af547c60fb51 · report
liebracket vinits5/PointNetLK/utils/so3.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · a253a6362a8213c9 · report
mat vinits5/PointNetLK/utils/se3.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 92b15d1f75b10f1b · report
mat vinits5/PointNetLK/utils/so3.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 9d3e60944e1061f1 · report
objread vinits5/PointNetLK/utils/mesh.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 52a9f7d06b228b77 · report
offread vinits5/PointNetLK/utils/mesh.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · e3a74959859b332c · report
postprocess_data vinits5/PointNetLK/utils/data_utils.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 8e8b11f58d8ca6c0 · report
preprocess_data vinits5/PointNetLK/utils/data_utils.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · b7f8841b68729bda · report
sinc1 vinits5/PointNetLK/utils/sinc.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · fa5ccc333d835363 · report
sinc1_dt vinits5/PointNetLK/utils/sinc.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · d6743b3739758b3c · report
sinc1_dt_rt vinits5/PointNetLK/utils/sinc.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 2db19ceaf8b62ec1 · report
sphere vinits5/PointNetLK/utils/partial_data.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · dfc07249e3b845a4 · report
sphere_torch vinits5/PointNetLK/utils/partial_data.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 8545abb55e61a6e6 · report
symfn_avg vinits5/PointNetLK/model.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 7a2618862db48ff9 · report
symfn_max vinits5/PointNetLK/model.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 0531ab2ada61e54e · report

Tasks

Computational EfficiencyPoint Cloud RegistrationRolling Shutter Correction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Registration 3DMatch (at least 30% overlapped - FCGF setting) PointNetLK Recall (0.3m, 15 degrees) 1.61 #14 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.

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