Papers › PointConv: Deep Convolutional Networks on 3D Point Clouds

PointConv: Deep Convolutional Networks on 3D Point Clouds

17 Nov 2018CVPR 2019 6arXiv:1811.07246archive 2025-07-28

Wenxuan Wu, Zhongang Qi, Li Fuxin

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named PointConv. PointConv can be applied on point clouds to build deep convolutional networks. We treat convolution kernels as nonlinear functions of the local coordinates of 3D points comprised of weight and density functions. With respect to a given point, the weight functions are learned with multi-layer perceptron networks and density functions through kernel density estimation. The most important contribution of this work is a novel reformulation proposed for efficiently computing the weight functions, which allowed us to dramatically scale up the network and significantly improve its performance. The learned convolution kernel can be used to compute translation-invariant and permutation-invariant convolution on any point set in the 3D space. Besides, PointConv can also be used as deconvolution operators to propagate features from a subsampled point cloud back to its original resolution. Experiments on ModelNet40, ShapeNet, and ScanNet show that deep convolutional neural networks built on PointConv are able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds. Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.

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 15 code samples harvested from 4 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 14 samples from 3 repositories, 13 ran (3 with no instrument failure; 10 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DylanWusee/pointconv officialmentioned in papermentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
DylanWusee/pointconv_pytorch mentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (7 instrument-failed) · 1 unverified report
ECE685-FinalProject/3D-object-recognition mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
Ghailen-Ben-Achour/PointConv_segmentation mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
THHHomas/mls mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
Young98CN/pointconv_pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
dgriffiths3/pointconv-tensorflow2 mentioned on GitHubtfSyntology: not harvested report
koritsky/pointconv mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
vinits5/learning3d mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 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

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
4ran · our draft was wrong
6ran; the contract check could not run
1ran
1unverified

Licence: 6 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

DylanWusee/pointconv official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
add_vote evaluate_scannet.py ran · honoured contract licence not identified · pointer only · 0182cf468fff0658 · report fixture: signature vote_label_pool:ndarray/2/int, point_idx:Tensor/2/int, pred_label:Tensor/2/int · returned ndarray · level recorded 2026-09-22
DylanWusee/pointconv_pytorch community (archive-listed) 11 samples, 10 ran (7 instrument-failed) · 1 unverified
compute_cat_iou utils/utils.py ran MIT (permissive) · aa14435a8eb76c18 · report fixture: signature pred:Tensor/3/float, target:Tensor/2/int, iou_tabel:ndarray/2/float · returned tuple · level recorded 2026-09-26
farthest_point_sample in 64 papers data_utils/ModelNetDataLoader.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · f80066a00e7156a2 · report fixture: signature point:ndarray/2/float, npoint:int/0/int · returned ndarray · level recorded 2026-09-25
index_points in 49 papers utils/pointconv_util.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 573cb024ea47999f · report fixture: returned Tensor · level recorded 2026-09-22
normalize_data in 32 papers
census: 7 implementations from 7 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
provider.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 59e9008f0a3743f1 · report fixture: signature batch_data:ndarray/3/float · returned ndarray · level recorded 2026-09-24
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
data_utils/ModelNetDataLoader.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 4783fbece52f500e · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-22
shuffle_data in 34 papers provider.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 06353aadebc1724b · report fixture: signature data:ndarray/3/float, labels:ndarray/1/int · returned tuple · level recorded 2026-09-24
shuffle_points in 13 papers provider.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · a97f76b9c0811c93 · report fixture: signature batch_data:ndarray/3/float · returned ndarray · level recorded 2026-09-22
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
utils/pointconv_util.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 580dee6761649b29 · report fixture: returned Tensor · level recorded 2026-09-22
timeit in 59 papers utils/pointconv_util.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · b1227ddb721e2999 · report fixture: signature tag:str/0/str, t:float/0/float · returned float · level recorded 2026-09-26
to_categorical in 25 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
utils/utils.py ran · our draft was wrong MIT (permissive) · 767b99615bbda28e · report fixture: signature y:Tensor/1/int, num_classes:int/0/int · returned Tensor · level recorded 2026-09-22
test in 377 papers utils/utils.py unverified MIT (permissive) · 3fbd70fccfa67f08 · report
THHHomas/mls community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
generate_new_view eval_cls_conv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 47e1f8a08b59cb74 · report fixture: signature points:ndarray/3/float · returned ndarray · level recorded 2026-09-22
rotate_point_cloud_by_angle in 5 papers eval_cls_conv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 1e76fe3207797dd7 · report fixture: signature data:ndarray/2/float, rotation_angle:float/0/float · returned ndarray · level recorded 2026-09-22
vinits5/learning3d community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
create_pointconv models/pointconv.py ran · our draft was wrong MIT (permissive) · 02c94555b6069d2e · report fixture: signature classifier:bool/0/bool, pretrained:NoneType/0/? · returned type · level recorded 2026-09-22

Tasks

3D Part Segmentation3D Point Cloud ClassificationDensity EstimationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation IntrA PointConv DSC (A) 86.52 #2 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointConv DSC (V) 97.18 #2 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointConv IoU (A) 79.53 #2 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointConv IoU (V) 94.65 #2 of 7 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointConv Class Average IoU 82.8 #43 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointConv Instance Average IoU 85.7 #43 of 67 Archive leaderboard report
3D Point Cloud Classification IntrA PointConv F1 score (5-fold) 0.883 #5 of 12 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointConv Overall Accuracy 92.5 #87 of 111 Archive leaderboard report
Semantic Segmentation ScanNet PointConv test mIoU 55.6 #31 of 45 Archive leaderboard report
Semantic Segmentation ScanNet PointConv val mIoU 61.0 #31 of 45 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