Papers › KPConv: Flexible and Deformable Convolution for Point Clouds

KPConv: Flexible and Deformable Convolution for Point Clouds

18 Apr 2019ICCV 2019 10arXiv:1904.08889archive 2025-07-28

Hugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, François Goulette, Leonidas J. Guibas

We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KPConv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Thanks to a regular subsampling strategy, KPConv is also efficient and robust to varying densities. Whether they use deformable KPConv for complex tasks, or rigid KPconv for simpler tasks, our networks outperform state-of-the-art classification and segmentation approaches on several datasets. We also offer ablation studies and visualizations to provide understanding of what has been learned by KPConv and to validate the descriptive power of deformable KPConv.

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="1904.08889")

Code

Syntology Ran 5 of 12 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 6 samples from 1 repository, 0 ran; community (archive-listed): 6 samples from 2 repositories, 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.

HuguesTHOMAS/KPConv officialmentioned in papermentioned on GitHubtfMIT report
Arjun-NA/KPConv_for_DALES mentioned on GitHubtfMIT report
HuguesTHOMAS/KPConv-PyTorch mentioned on GitHubpytorch report
JohnRomanelis/KPConv_torch_geometric mentioned on GitHubpytorch report
XuyangBai/KPConv.pytorch mentioned on GitHubpytorch report
Yacovitch/EyeNet mentioned on GitHubtfNOASSERTION report
genglinliu/KPConv_Pytorch mentioned on GitHubpytorch report
ldkong1205/Robo3D mentioned on GitHubpytorch report
plusmultiply/mprm mentioned on GitHubtfMIT 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

12 samples harvested; 5 ran; 1 honoured the contract we drafted; 7 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 · honoured contract
3ran · our draft was wrong
1ran · fixture could not drive it
7unverified

Licence: 3 of the 12 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 3 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.

IoU_class_metrics HuguesTHOMAS/KPConv/plot_convergence.py official repository unverified MIT (permissive) · 814a2fe9241bee1e · report
IoU_multi_metrics HuguesTHOMAS/KPConv/plot_convergence.py official repository unverified MIT (permissive) · 09d5696850a35aee · report
bias_variable HuguesTHOMAS/KPConv/models/network_blocks.py official repository unverified MIT (permissive) · 6a88f1ae24fa26b2 · report
ind_max_pool HuguesTHOMAS/KPConv/models/network_blocks.py official repository unverified MIT (permissive) · 4383ecd8cc0719fa · report
running_mean HuguesTHOMAS/KPConv/plot_convergence.py official repository unverified MIT (permissive) · 2e38027f9a1a89e6 · report
weight_variable HuguesTHOMAS/KPConv/models/network_blocks.py official repository unverified MIT (permissive) · 5a6188c7d118c3fc · report
closest_pool isl-org/Open3D-ML/ml3d/torch/models/kpconv.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · bbafdd82ae3987bf · report
create_3D_rotations HuguesTHOMAS/KPConv-PyTorch/kernels/kernel_points.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · c545a5b0a698e295 · report
gather isl-org/Open3D-ML/ml3d/torch/models/kpconv.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · 9a89c500824a1c5c · report
kernel_point_optimization_debug HuguesTHOMAS/KPConv-PyTorch/kernels/kernel_points.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · a40d478bb51450e9 · report
radius_gaussian isl-org/Open3D-ML/ml3d/torch/models/kpconv.py community (archive-listed) ran · our draft was wrong fingerprinted licence not identified · pointer only · c0186f8ddb0bc115 · report
p2p_fitting_regularizer HuguesTHOMAS/KPConv-PyTorch/models/architectures.py community (archive-listed) unverified MIT (permissive) · 9b6e188d38ea6880 · report

Tasks

3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationDescriptiveLIDAR Semantic SegmentationRobust 3D Semantic SegmentationScene SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part KPConv Class Average IoU 85.1 #25 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part KPConv Instance Average IoU 86.4 #25 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 KPConv Overall Accuracy 92.9 #79 of 111 Archive leaderboard report
3D Semantic Segmentation DALES KPConv Model size 14M #1 of 9 Archive leaderboard report
3D Semantic Segmentation DALES KPConv Overall Accuracy 97.8 #1 of 9 Archive leaderboard report
3D Semantic Segmentation DALES KPConv mIoU 81.1 #1 of 9 Archive leaderboard report
3D Semantic Segmentation STPLS3D KpConv mIOU 53.73 #1 of 6 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI KPConv test mIoU 58.8% #23 of 45 Archive leaderboard report
3D Semantic Segmentation SensatUrban KPConv mIoU 57.58 #4 of 8 Archive leaderboard report
LIDAR Semantic Segmentation Paris-Lille-3D KPConv deform mIOU 0.759 #5 of 9 Archive leaderboard report
Robust 3D Semantic Segmentation SemanticKITTI-C KPConv mean Corruption Error (mCE) 99.54% #2 of 22 Archive leaderboard report
Scene Segmentation ScanNet KPConv 3DIoU 68.6 #3 of 3 Archive leaderboard report
Semantic Segmentation S3DIS KPConv Mean IoU 70.6 #23 of 54 Archive leaderboard report
Semantic Segmentation S3DIS KPConv Number of params 14.1M #23 of 54 Archive leaderboard report
Semantic Segmentation S3DIS KPConv Params (M) 14.1 #23 of 54 Archive leaderboard report
Semantic Segmentation S3DIS KPConv mAcc 79.1 #23 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 KPConv Number of params 14.1M #42 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 KPConv mAcc 72.8 #42 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 KPConv mIoU 67.1 #42 of 61 Archive leaderboard report
Semantic Segmentation ScanNet KpConv test mIoU 68.0 #29 of 45 Archive leaderboard report
Semantic Segmentation ScanNet KpConv val mIoU 69.2 #29 of 45 Archive leaderboard report
Semantic Segmentation Semantic3D KPConv mIoU 74.6% #7 of 17 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

Convolution

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