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 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

Syntology 12 code samples harvested from 3 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 6 samples from 2 repositories, 5 ran (1 with no instrument failure; 4 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

HuguesTHOMAS/KPConv officialmentioned in papermentioned on GitHubtfMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
Arjun-NA/KPConv_for_DALES mentioned on GitHubtfMITSyntology: not harvested report
HuguesTHOMAS/KPConv-PyTorch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
JohnRomanelis/KPConv_torch_geometric mentioned on GitHubpytorchSyntology: not harvested report
XuyangBai/KPConv.pytorch mentioned on GitHubpytorchSyntology: not harvested report
Yacovitch/EyeNet mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
genglinliu/KPConv_Pytorch mentioned on GitHubpytorchSyntology: not harvested report
ldkong1205/Robo3D mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation (arXiv:2312.04484; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
plusmultiply/mprm mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds (arXiv:2003.13035; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
isl-org/Open3D-ML pytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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.

1ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
4ran
3unverified

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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

HuguesTHOMAS/KPConv official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
IoU_class_metrics plot_convergence.py ran MIT (permissive) · 814a2fe9241bee1e · report fixture: signature all_IoUs:list/1/ndarray, smooth_n:int/0/int · returned tuple · level recorded 2026-09-25
IoU_multi_metrics plot_convergence.py ran MIT (permissive) · 09d5696850a35aee · report fixture: signature all_IoUs:list/1/list, smooth_n:int/0/int · returned tuple · level recorded 2026-09-25
bias_variable in 24 papers models/network_blocks.py ran MIT (permissive) · 6a88f1ae24fa26b2 · report fixture: signature shape:tuple/1/int · returned ResourceVariable · level recorded 2026-09-25
running_mean in 13 papers plot_convergence.py ran fingerprinted MIT (permissive) · 2e38027f9a1a89e6 · report fixture: signature signal:ndarray/1/float, n:int/0/int, axis:int/0/int · returned ndarray · level recorded 2026-09-25
ind_max_pool in 5 papers models/network_blocks.py unverified MIT (permissive) · 4383ecd8cc0719fa · report
weight_variable in 29 papers models/network_blocks.py unverified MIT (permissive) · 5a6188c7d118c3fc · report
HuguesTHOMAS/KPConv-PyTorch community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
create_3D_rotations in 5 papers kernels/kernel_points.py ran · honoured contract fingerprinted MIT (permissive) · c545a5b0a698e295 · report fixture: signature axis:ndarray/2/float, angle:ndarray/1/float · returned ndarray · level recorded 2026-09-22
kernel_point_optimization_debug in 8 papers kernels/kernel_points.py ran · our draft was wrong fingerprinted MIT (permissive) · a40d478bb51450e9 · report fixture: signature radius:float/0/float, num_points:int/0/int, num_kernels:int/0/int, dimension:int/0/int, fixed:str/0/str, ratio:float/0/float, verbose:int/0/int · returned tuple · level recorded 2026-09-22
p2p_fitting_regularizer models/architectures.py unverified MIT (permissive) · 9b6e188d38ea6880 · report
isl-org/Open3D-ML community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
closest_pool in 7 papers ml3d/torch/models/kpconv.py ran · our draft was wrong licence not identified · pointer only · bbafdd82ae3987bf · report fixture: signature x:Tensor/2/float, inds:Tensor/2/int · returned Tensor · level recorded 2026-09-22
gather in 75 papers ml3d/torch/models/kpconv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 9a89c500824a1c5c · report fixture: signature x:Tensor/3/float, idx:Tensor/2/int, method:int/0/int · returned Tensor · level recorded 2026-09-22
radius_gaussian in 11 papers ml3d/torch/models/kpconv.py ran · our draft was wrong fingerprinted licence not identified · pointer only · c0186f8ddb0bc115 · report fixture: signature sq_r:Tensor/3/float, sig:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22

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