Papers › PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

7 Jun 2017NeurIPS 2017 12arXiv:1706.02413archive 2025-07-28

Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas

Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 67 code samples harvested from 17 repositories linked to this paper: 36 ran (of which 31 constructed an object rather than computing a result; 33 with no instrument failure: 0 honoured, 0 violated, 33 with no contract checked; 3 where Syntology's instrument failed) · 31 unverified. Where Syntology's instrument failed: 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 67 samples from 17 repositories, 36 ran (33 with no instrument failure; 3 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 14 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

68 repositories listed; official and paper-mentioned ones first.

AsahiLiu/PointDetectron mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
FlowWind1999/pointnet-2 mentioned on GitHubtfSyntology: not harvested report
Ghailen-Ben-Achour/PointNet2_Segmentation mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
Harut0726/votenet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
JohnsonSign/PointCMP mentioned on GitHubpytorchSyntology: not harvested report
LONG-9621/PointNet- mentioned on GitHubtfSyntology: not harvested report
LONG-9621/VoteNet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Hough Voting for 3D Object Detection in Point Clouds (arXiv:1904.09664; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
LinZhuoChen/pointnet2_multi_gpu mentioned on GitHubtfSyntology: not harvested report
Lonepic/SPIB mentioned on GitHubpytorchSyntology: not harvested report
Lw510107/PointNet mentioned on GitHubtfSyntology: not harvested report
SY-Xuan/pointnet_plus_plus_paddlepaddle mentioned on GitHubpaddleSyntology: not harvested report
Xiangxu-0103/Octant-CNN mentioned on GitHubtfSyntology: not harvested report
asalarpour/Point_GN mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
brbzjl/pointnet2 mentioned on GitHubtfSyntology: not harvested report
caizeyu1992/pointnet2 mentioned on GitHubmindsporeSyntology: not harvested report
charlesq34/pointnet2 mentioned on GitHubtfSyntology: not harvested report
curryyuan/x-trans2cap mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
dfki-av/mikasa-3dvg mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
dgriffiths3/pointnet2-tensorflow2 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
facebookresearch/imvotenet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes (arXiv:2001.10692; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
facebookresearch/votenet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rotationally Equivariant 3D Object Detection (arXiv:2204.13630; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
ftdlyc/pointnet_pytorch 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
hehefan/P4Transformer mentioned on GitHubpytorchSyntology: not harvested report
hehefan/PSTNet2 mentioned on GitHubpytorchSyntology: not harvested report
hehefan/Point-Spatio-Temporal-Convolution mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators (arXiv:2605.20978; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
hehefan/PointRNN mentioned on GitHubtfSyntology: not harvested report
hehefan/PointRNN-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
hoangcuongbk80/VoteGrasp mentioned on GitHubpytorchSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
houseleo/pointnet mentioned on GitHubtfSyntology: not harvested report
iballester/SPiKE mentioned on GitHubpytorchSyntology: not harvested report
ikh-innovation/roboweldar-votenet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Hough Voting for 3D Object Detection in Point Clouds (arXiv:1904.09664; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
johnsonsign/mast-pre mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos (arXiv:2308.09245; that paper's own run record: 8 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; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
joyhsu0504/ns3d mentioned on GitHubpytorchSyntology: not harvested report
llzlcl/pointcloud-segment mentioned on GitHubtfSyntology: not harvested report
nickgkan/beauty_detr mentioned on GitHubpytorchSyntology: not harvested report
nickgkan/butd_detr mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
open-air-sun/pq-transformer mentioned on GitHubpytorchSyntology: not harvested report
referit3d/referit3d mentioned on GitHubpytorchSyntology: 12 samples, 8 ran (0 instrument-failed) · 4 unverified report
rusty1s/pytorch_cluster mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs (arXiv:1704.02901; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. report
shaygu62/Protein-Classification mentioned on GitHubSyntology: not harvested report
sshaoshuai/Pointnet2.PyTorch mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
tao-tao-tao-tao-tao/diffusion_suction mentioned on GitHubpytorchSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
thu17cyz/3DIoUMatch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
timothylimyl/PointNet-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
tingxueronghua/dpke mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection (arXiv:2401.05011; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
tonysy/pointnet2_tf mentioned on GitHubtfSyntology: not harvested report
witignite/Frustum-PointNet mentioned on GitHubtfSyntology: not harvested report
xurui1217/pointnet2-master mentioned on GitHubtfSyntology: not harvested report
zaiweizhang/H3DNet mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
zenroad/modifypointnet mentioned on GitHubtfSyntology: not harvested report
zhh6425/LocalContextPropagation mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
zhh6425/MotionPointNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Exploring PDE Modeling for Point Cloud Video Representation Learning (arXiv:2404.04720; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zyang-ur/SAT mentioned on GitHubpytorchSyntology: 13 samples, 10 ran (0 instrument-failed) · 3 unverified report
gitee.com/gai-shaoyan/mind3d Syntology: not harvested report
2023-MindSpore-1/ms-code-223 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-223 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-8 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-paper-code-3/code4 mindsporeSyntology: not harvested report
airalcorn2/parking-lot-pointnetplusplus pytorchSyntology: not harvested report
alililia/ms_extend mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
alililia/ms_extend mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
erikwijmans/Pointnet2_PyTorch pytorchSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; 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) · 1 unverified); nothing checks that they implement this paper's method. report
princeton-vl/SimpleView pytorchSyntology: 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), Dynamic Graph CNN for Learning on Point Clouds (arXiv:1801.07829; that paper's own run record: 16 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 28 unverified) and Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (arXiv:2106.05304; that paper's own run record: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
yanx27/Pointnet_Pointnet2_pytorch pytorchSyntology: 2 samples, 2 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

67 samples harvested: 36 ran (of which 31 constructed an object rather than computing a result; 33 with no instrument failure: 0 honoured, 0 violated, 33 with no contract checked; 3 where Syntology's instrument failed) · 31 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.

3ran; the contract check could not run
33ran
31unverified

Licence: 26 of the 67 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 17 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”. For 15 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

AsahiLiu/PointDetectron community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
QueryAndGroup pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic MIT (permissive) · 6023143b3d4c2b8e · report fixture: returned QueryAndGroup · level recorded 2026-09-22
PointnetSAModule pointnet2/pointnet2_modules.py unverified MIT (permissive) · 1b0bdf31bf17378b · report
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified MIT (permissive) · 6d3f7e94b9d2b11b · report
Ghailen-Ben-Achour/PointNet2_Segmentation community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
PointNetSetAbstraction in 7 papers models/pointnet2_cls_ssg.py ran MIT (permissive) · f66046a728fcaaa4 · report fixture: signature xyz:Tensor/3/float, points:Tensor/3/float · returned tuple · level recorded 2026-09-24
sample_and_group in 10 papers models/pointnet2_cls_ssg.py ran; the contract check could not run (RAISES) MIT (permissive) · 70d28914ddac1077 · report fixture: signature npoint:int/0/int, radius:float/0/float, nsample:int/0/int, xyz:Tensor/3/float, points:Tensor/3/float, returnfps:bool/0/bool · returned tuple · level recorded 2026-09-24
get_model in 368 papers models/pointnet2_cls_ssg.py unverified MIT (permissive) · fd3561eefae695d6 · report
Harut0726/votenet community (archive-listed) 1 sample, 0 ran · 1 unverified
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified MIT (permissive) · a3e240dde91b9210 · report
asalarpour/Point_GN community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
build_shared_mlp in 7 papers pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c80f9bbb31e6cb9f · report fixture: signature mlp_spec:list/1/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py unverified no licence file found · pointer only · 843c26df3d1ce95d · report
_PointnetSAModuleBase in 8 papers pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py unverified no licence file found · pointer only · fcf8a72210d6405a · report
curryyuan/x-trans2cap community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
GroupAll lib/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 445cffa437113b80 · report fixture: returned GroupAll · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers lib/pointnet2/pointnet2_modules.py unverified Apache-2.0 (permissive) · 46d072d568750005 · report
dfki-av/mikasa-3dvg community (archive-listed) 2 samples, 0 ran · 2 unverified
PointNetPP models/point_net_pp.py unverified no licence file found · pointer only · 7ff6372868b293d9 · report
PointnetSAModuleMSG in 9 papers models/point_net_pp.py unverified no licence file found · pointer only · 613ddd5378be9c11 · report
dgriffiths3/pointnet2-tensorflow2 community (archive-listed) 1 sample, 0 ran · 1 unverified
Pointnet_SA_MSG pnet2_layers/layers.py unverified no licence file found · pointer only · 855fbabeb3a336f4 · report
hoangcuongbk80/VoteGrasp community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
BallQuery pointnet2/pointnet2_modules.py ran no licence file found · pointer only · fdd72fc42b06427f · report fixture: returned BallQuery · level recorded 2026-09-22
FurthestPointSampling pointnet2/pointnet2_modules.py ran no licence file found · pointer only · 018e0e61ae702455 · report fixture: returned FurthestPointSampling · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified no licence file found · pointer only · 793ed3a4ee8d7bf4 · report
QueryAndGroup pointnet2/pointnet2_modules.py unverified no licence file found · pointer only · 5d1e43f12483593d · report
_PointnetSAModuleBase in 8 papers pointnet2/pointnet2_modules.py unverified no licence file found · pointer only · d068c3e73bb13c3c · report
nickgkan/butd_detr community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
GroupAll pointnet2/pointnet2_modules.py ran · metamorphic tier: invariant licence not identified · pointer only · b9995eaf8da14955 · report fixture: signature xyz:Tensor/3/float, new_xyz:Tensor/3/float, features:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified licence not identified · pointer only · 849da9ddf3201c42 · report
referit3d/referit3d community (archive-listed) 12 samples, 8 ran (0 instrument-failed) · 4 unverified
BatchNorm2d in 9 papers referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic MIT (permissive) · f9032ebfafd355b4 · report fixture: returned BatchNorm2d · level recorded 2026-09-22
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 11786f1c29af0e47 · report fixture: returned Conv2d · level recorded 2026-09-22
GroupAll referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ff97c3b6610cf824 · report fixture: returned GroupAll · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic MIT (permissive) · d53b2e702a829fb0 · report fixture: returned PointnetSAModuleMSG · level recorded 2026-09-22
QueryAndGroup referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic MIT (permissive) · 87a6f4d31460171e · report fixture: returned QueryAndGroup · level recorded 2026-09-22
SharedMLP in 7 papers referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 31e40d80b30e1b2c · report fixture: returned SharedMLP · level recorded 2026-09-22
_BNBase referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f87521261bb11483 · report fixture: returned _BNBase · level recorded 2026-09-22
_ConvBase referit3d/models/backbone/point_net_pp.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 256c9a6ac7df5930 · report fixture: returned _ConvBase · level recorded 2026-09-22
PointNetPP referit3d/models/backbone/point_net_pp.py unverified MIT (permissive) · 95614125c07b84a3 · report
PointnetSAModule referit3d/models/backbone/point_net_pp.py unverified MIT (permissive) · fcea688e1b440469 · report
_PointnetSAModuleBase in 8 papers referit3d/models/backbone/point_net_pp.py unverified MIT (permissive) · 0ae12792e37fd27a · report
break_up_pc referit3d/models/backbone/point_net_pp.py unverified MIT (permissive) · 2072a4df477eeee7 · report
sshaoshuai/Pointnet2.PyTorch community (archive-listed) 2 samples, 0 ran · 2 unverified
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified MIT (permissive) · e007e97b1d9d744b · report
_PointnetSAModuleBase in 8 papers pointnet2/pointnet2_modules.py unverified MIT (permissive) · e185951b532deb50 · report
tao-tao-tao-tao-tao/diffusion_suction community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
train/models/backbone2/pointnet2/pointnet2_backbone.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 13cd8bfa92565fb3 · report fixture: returned Conv2d · level recorded 2026-09-22
GroupAll train/models/backbone2/pointnet2/pointnet2_backbone.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bdb62dc3b4da8637 · report fixture: returned GroupAll · level recorded 2026-09-22
PointnetFPModule in 8 papers train/models/backbone2/pointnet2/pointnet2_backbone.py ran · metamorphic tier: deterministic no licence file found · pointer only · 88a3d7070038a37c · report fixture: returned PointnetFPModule · level recorded 2026-09-22
QueryAndGroup train/models/backbone2/pointnet2/pointnet2_backbone.py ran · metamorphic tier: deterministic no licence file found · pointer only · 32e0c6849f5f0893 · report fixture: returned QueryAndGroup · level recorded 2026-09-22
SharedMLP in 7 papers train/models/backbone2/pointnet2/pointnet2_backbone.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · dbd9c5b5bde4b57b · report fixture: returned SharedMLP · level recorded 2026-09-22
_ConvBase train/models/backbone2/pointnet2/pointnet2_backbone.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 37537db27757694f · report fixture: returned _ConvBase · level recorded 2026-09-22
Pointnet2Backbone train/models/backbone2/pointnet2/pointnet2_backbone.py unverified no licence file found · pointer only · 7ffe30c65652d376 · report
PointnetSAModule train/models/backbone2/pointnet2/pointnet2_backbone.py unverified no licence file found · pointer only · b3b9df5e5970a1a7 · report
PointnetSAModuleMSG in 9 papers train/models/backbone2/pointnet2/pointnet2_backbone.py unverified no licence file found · pointer only · 1d8dff9fef819904 · report
_PointnetSAModuleBase in 8 papers train/models/backbone2/pointnet2/pointnet2_backbone.py unverified no licence file found · pointer only · ce03a592a53ad8c1 · report
thu17cyz/3DIoUMatch community (archive-listed) 1 sample, 0 ran · 1 unverified
Pointnet2Backbone models/backbone_module.py unverified no licence file found · pointer only · 86d8804e1b24718b · report
zaiweizhang/H3DNet community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
QueryAndGroup pointnet2/pointnet2_modules.py ran MIT (permissive) · 66b3e1fb36ee440b · report fixture: returned QueryAndGroup · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified MIT (permissive) · 1788ad2f156a1b3d · report
_PointnetSAModuleBase in 8 papers pointnet2/pointnet2_modules.py unverified MIT (permissive) · b0b3d7766fcc0b36 · report
zhh6425/LocalContextPropagation community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
QueryAndGroup pointnet2/pointnet2_modules.py ran no licence file found · pointer only · bf4563a947bf0bd6 · report fixture: returned QueryAndGroup · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers pointnet2/pointnet2_modules.py unverified no licence file found · pointer only · a7ce6f090a331749 · report
zyang-ur/SAT community (archive-listed) 13 samples, 10 ran (0 instrument-failed) · 3 unverified
BallQuery referit3d/external_tools/pointnet2/pointnet2_modules.py ran MIT (permissive) · fb26ce705d6a2cb9 · report fixture: returned BallQuery · level recorded 2026-09-22
BatchNorm2d in 9 papers referit3d/external_tools/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic MIT (permissive) · 1eb36d9951cd4e0a · report fixture: returned BatchNorm2d · level recorded 2026-09-22
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
referit3d/external_tools/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 196a75317b3cf7d1 · report fixture: returned Conv2d · level recorded 2026-09-22
FurthestPointSampling referit3d/external_tools/pointnet2/pointnet2_modules.py ran MIT (permissive) · f038cc7c8955a963 · report fixture: returned FurthestPointSampling · level recorded 2026-09-22
GatherOperation referit3d/external_tools/pointnet2/pointnet2_modules.py ran MIT (permissive) · 3c75be14968690dc · report fixture: returned GatherOperation · level recorded 2026-09-22
GroupAll referit3d/external_tools/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 994fead02ef5cbd6 · report fixture: returned GroupAll · level recorded 2026-09-22
GroupingOperation referit3d/external_tools/pointnet2/pointnet2_modules.py ran MIT (permissive) · 4d80a2b4a0fba485 · report fixture: returned GroupingOperation · level recorded 2026-09-22
SharedMLP in 7 papers referit3d/external_tools/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3ac6212f679dac7c · report fixture: returned SharedMLP · level recorded 2026-09-22
_BNBase referit3d/external_tools/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic MIT (permissive) · c164cd7b73f4eeab · report fixture: returned _BNBase · level recorded 2026-09-22
_ConvBase referit3d/external_tools/pointnet2/pointnet2_modules.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · baee501048c6a68c · report fixture: returned _ConvBase · level recorded 2026-09-22
PointnetSAModuleMSG in 9 papers referit3d/external_tools/pointnet2/pointnet2_modules.py unverified MIT (permissive) · a80a54dddb6349ae · report
QueryAndGroup referit3d/external_tools/pointnet2/pointnet2_modules.py unverified MIT (permissive) · 4d94f2dd93d310a4 · report
_PointnetSAModuleBase in 8 papers referit3d/external_tools/pointnet2/pointnet2_modules.py unverified MIT (permissive) · 1e00adaf9c01804c · report
yanx27/Pointnet_Pointnet2_pytorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
PointNetSetAbstraction in 7 papers models/pointnet2_utils.py ran MIT (permissive) · b7bc001da9322423 · report fixture: returned PointNetSetAbstraction · level recorded 2026-09-22
sample_and_group in 10 papers models/pointnet2_utils.py ran; the contract check could not run (RAISES) MIT (permissive) · ad5401ceab4ea9b6 · report fixture: signature npoint:int/0/int, radius:float/0/float, nsample:int/0/int, xyz:Tensor/3/float, points:Tensor/3/float, returnfps:bool/0/bool · returned tuple · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

17 assemblies on this paper: 17 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

17 sibling assemblies for PointNet++ (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 17 sibling assemblies; the other 5 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for PointNet++ (graph method: PointNet++). 13 bricks; individually on a fixture: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModuleMSG entry · level 0 · unverified · a80a54dddb6349ae
  2. GroupAll helper · level 1 · ran · 994fead02ef5cbd6
  3. QueryAndGroup helper · level 0 · unverified · 4d94f2dd93d310a4
  4. SharedMLP model · level 1 · ran · 3ac6212f679dac7c
  5. _PointnetSAModuleBase helper · level 0 · unverified · 1e00adaf9c01804c
  6. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  7. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  8. _ConvBase helper · level 1 · ran · baee501048c6a68c
  9. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  10. BallQuery helper · level 1 · ran · fb26ce705d6a2cb9
  11. FurthestPointSampling helper · level 1 · ran · f038cc7c8955a963
  12. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  13. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 13 bricks; individually on a fixture: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModuleMSG entry · level 0 · unverified · 793ed3a4ee8d7bf4
  2. GroupAll helper · level 1 · ran · 5bb3d8214726b8f7
  3. QueryAndGroup helper · level 0 · unverified · 5d1e43f12483593d
  4. SharedMLP helper · level 1 · ran · 3ac6212f679dac7c
  5. _PointnetSAModuleBase helper · level 0 · unverified · d068c3e73bb13c3c
  6. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  7. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  8. _ConvBase helper · level 1 · ran · baee501048c6a68c
  9. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  10. BallQuery helper · level 1 · ran · fdd72fc42b06427f
  11. FurthestPointSampling helper · level 1 · ran · 018e0e61ae702455
  12. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  13. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 18 bricks; individually on a fixture: 14 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 14 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. Pointnet2Backbone entry · level 0 · unverified · 7ffe30c65652d376
  2. PointnetFPModule model · level 1 · ran · 88a3d7070038a37c
  3. PointnetSAModule model · level 0 · unverified · b3b9df5e5970a1a7
  4. SharedMLP helper · level 1 · ran · dbd9c5b5bde4b57b
  5. PointnetSAModuleMSG model · level 0 · unverified · 1d8dff9fef819904
  6. Conv2d helper · level 1 · ran · 13cd8bfa92565fb3
  7. GroupAll helper · level 1 · ran · bdb62dc3b4da8637
  8. QueryAndGroup helper · level 1 · ran · 32e0c6849f5f0893
  9. _PointnetSAModuleBase helper · level 0 · unverified · ce03a592a53ad8c1
  10. BatchNorm2d helper · level 1 · ran · ea90589983c7d4fb
  11. _ConvBase helper · level 1 · ran · 37537db27757694f
  12. _BNBase helper · level 1 · ran · 359fcb0c4f682234
  13. BallQuery helper · level 1 · ran · fb26ce705d6a2cb9
  14. FurthestPointSampling helper · level 1 · ran · f038cc7c8955a963
  15. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  16. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485
  17. ThreeInterpolate helper · level 1 · ran · 565863bfed9f02fc
  18. ThreeNN helper · level 1 · ran · 11f8d19732aa2254

harvested Assembly for PointNet++ (graph method: PointNet++). 14 bricks; individually on a fixture: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModule entry · level 0 · unverified · 1b0bdf31bf17378b
  2. PointnetSAModuleMSG helper · level 0 · unverified · 6d3f7e94b9d2b11b
  3. GroupAll helper · level 1 · ran · 5bb3d8214726b8f7
  4. QueryAndGroup helper · level 1 · ran · 6023143b3d4c2b8e
  5. SharedMLP helper · level 1 · ran · 3ac6212f679dac7c
  6. _PointnetSAModuleBase helper · level 0 · unverified · 1e00adaf9c01804c
  7. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  8. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  9. _ConvBase helper · level 1 · ran · baee501048c6a68c
  10. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  11. BallQuery helper · level 1 · ran · fb26ce705d6a2cb9
  12. FurthestPointSampling sampler · level 1 · ran · f038cc7c8955a963
  13. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  14. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 13 bricks; individually on a fixture: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModuleMSG entry · level 0 · unverified · a3e240dde91b9210
  2. GroupAll helper · level 1 · ran · 5bb3d8214726b8f7
  3. QueryAndGroup helper · level 0 · unverified · 4d94f2dd93d310a4
  4. SharedMLP model · level 1 · ran · 3ac6212f679dac7c
  5. _PointnetSAModuleBase helper · level 0 · unverified · 1e00adaf9c01804c
  6. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  7. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  8. _ConvBase helper · level 1 · ran · baee501048c6a68c
  9. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  10. BallQuery helper · level 1 · ran · fb26ce705d6a2cb9
  11. FurthestPointSampling helper · level 1 · ran · f038cc7c8955a963
  12. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  13. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 13 bricks; individually on a fixture: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModuleMSG entry · level 0 · unverified · 46d072d568750005
  2. GroupAll helper · level 1 · ran · 445cffa437113b80
  3. QueryAndGroup helper · level 0 · unverified · 5d1e43f12483593d
  4. SharedMLP helper · level 1 · ran · 3ac6212f679dac7c
  5. _PointnetSAModuleBase helper · level 0 · unverified · d068c3e73bb13c3c
  6. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  7. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  8. _ConvBase helper · level 1 · ran · baee501048c6a68c
  9. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  10. BallQuery helper · level 1 · ran · fdd72fc42b06427f
  11. FurthestPointSampling helper · level 1 · ran · 018e0e61ae702455
  12. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  13. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 16 bricks; individually on a fixture: 12 ran (of which 12 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 12 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointNetPP entry · level 0 · unverified · 95614125c07b84a3
  2. PointnetSAModule model · level 0 · unverified · fcea688e1b440469
  3. break_up_pc helper · level 0 · unverified · 2072a4df477eeee7
  4. PointnetSAModuleMSG model · level 1 · ran · d53b2e702a829fb0
  5. GroupAll helper · level 1 · ran · ff97c3b6610cf824
  6. QueryAndGroup helper · level 1 · ran · 87a6f4d31460171e
  7. SharedMLP helper · level 1 · ran · 31e40d80b30e1b2c
  8. _PointnetSAModuleBase model · level 0 · unverified · 0ae12792e37fd27a
  9. Conv2d helper · level 1 · ran · 11786f1c29af0e47
  10. BatchNorm2d helper · level 1 · ran · f9032ebfafd355b4
  11. _ConvBase helper · level 1 · ran · 256c9a6ac7df5930
  12. _BNBase helper · level 1 · ran · f87521261bb11483
  13. BallQuery helper · level 1 · ran · fb26ce705d6a2cb9
  14. FurthestPointSampling helper · level 1 · ran · f038cc7c8955a963
  15. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  16. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModuleMSG entry · level 0 · unverified · e007e97b1d9d744b
  2. _PointnetSAModuleBase helper · level 0 · unverified · e185951b532deb50

harvested Assembly for PointNet++ (graph method: PointNet++). 16 bricks; individually on a fixture: 13 ran (of which 13 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 13 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. Pointnet2Backbone entry · level 0 · unverified · 86d8804e1b24718b
  2. PointnetFPModule model · level 1 · ran · d53ad68b74734b36
  3. PointnetSAModuleVotes helper · level 0 · unverified · ee17b6fa95e4d8fa
  4. SharedMLP helper · level 1 · ran · 3ac6212f679dac7c
  5. GroupAll helper · level 1 · ran · 5bb3d8214726b8f7
  6. QueryAndGroup helper · level 0 · unverified · 5d1e43f12483593d
  7. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  8. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  9. _ConvBase helper · level 1 · ran · baee501048c6a68c
  10. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  11. BallQuery helper · level 1 · ran · fdd72fc42b06427f
  12. FurthestPointSampling helper · level 1 · ran · 018e0e61ae702455
  13. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  14. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485
  15. ThreeInterpolate helper · level 1 · ran · 565863bfed9f02fc
  16. ThreeNN helper · level 1 · ran · 11f8d19732aa2254

harvested Assembly for PointNet++ (graph method: PointNet++). 7 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointNetSetAbstraction entry · level 1 · ran · b7bc001da9322423
  2. sample_and_group helper · level 1 · ran; the contract check could not run (RAISES) · ad5401ceab4ea9b6
  3. sample_and_group_all helper · level 1 · ran; the contract check could not run · 851a7e1fdd8b809a
  4. farthest_point_sample helper · level 1 · ran; the contract check could not run · 8016bf9f4fcc1ce4
  5. index_points helper · level 1 · ran; the contract check could not run · 573cb024ea47999f
  6. query_ball_point helper · level 1 · ran; the contract check could not run · 45a0ca2d012bb9fe
  7. square_distance helper · level 1 · ran; the contract check could not run · 580dee6761649b29

harvested Assembly for PointNet++ (graph method: PointNet++). 13 bricks; individually on a fixture: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointnetSAModuleMSG entry · level 0 · unverified · a7ce6f090a331749
  2. GroupAll helper · level 1 · ran · 5bb3d8214726b8f7
  3. QueryAndGroup model · level 1 · ran · bf4563a947bf0bd6
  4. SharedMLP model · level 1 · ran · 3ac6212f679dac7c
  5. _PointnetSAModuleBase helper · level 0 · unverified · d068c3e73bb13c3c
  6. Conv2d helper · level 1 · ran · 196a75317b3cf7d1
  7. BatchNorm2d helper · level 1 · ran · 1eb36d9951cd4e0a
  8. _ConvBase helper · level 1 · ran · baee501048c6a68c
  9. _BNBase helper · level 1 · ran · c164cd7b73f4eeab
  10. BallQuery helper · level 1 · ran · fdd72fc42b06427f
  11. FurthestPointSampling helper · level 1 · ran · 018e0e61ae702455
  12. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  13. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485

harvested Assembly for PointNet++ (graph method: PointNet++). 15 bricks; individually on a fixture: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. PointNetPP entry · level 0 · unverified · 7ff6372868b293d9
  2. PointnetSAModuleMSG model · level 0 · unverified · 613ddd5378be9c11
  3. break_up_pc helper · level 0 · unverified · 775337099d9f9b3c
  4. GroupAll model · level 1 · ran · ff97c3b6610cf824
  5. QueryAndGroup model · level 1 · ran · 87a6f4d31460171e
  6. SharedMLP helper · level 1 · ran · 31e40d80b30e1b2c
  7. _PointnetSAModuleBase model · level 0 · unverified · 0ae12792e37fd27a
  8. Conv2d helper · level 1 · ran · 11786f1c29af0e47
  9. BatchNorm2d helper · level 1 · ran · f9032ebfafd355b4
  10. _ConvBase helper · level 1 · ran · 256c9a6ac7df5930
  11. _BNBase helper · level 1 · ran · f87521261bb11483
  12. BallQuery sampler · level 1 · ran · fb26ce705d6a2cb9
  13. FurthestPointSampling sampler · level 1 · ran · f038cc7c8955a963
  14. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  15. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485
  1. PointnetSAModuleMSG · a12fbf5b8d817922 · 13 bricks; individually on a fixture: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 11 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. PointnetSAModuleMSG · a13387c33f586f0d · 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. PointnetSAModuleMSG · c2763ff135b239b3 · 13 bricks; individually on a fixture: 10 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. Pointnet_SA_MSG · e2cdb4550f443a42 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. get_model · f5ea855e4ecf77cb · 8 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1706.02413") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationFew-Shot 3D Point Cloud ClassificationPerson Re-IdentificationPoint Cloud SegmentationSemantic SegmentationSupervised Only 3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation IntrA PointNet++ DSC (A) 84.64 #5 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointNet++ DSC (V) 96.48 #5 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointNet++ IoU (A) 76.38 #5 of 7 Archive leaderboard report
3D Part Segmentation IntrA PointNet++ IoU (V) 93.42 #5 of 7 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointNet++ Class Average IoU 81.9 #55 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointNet++ Instance Average IoU 85.1 #55 of 67 Archive leaderboard report
3D Point Cloud Classification IntrA PointNet++ F1 score (5-fold) 0.903 #4 of 12 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet++ Number of params 1.74M #101 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointNet++ Overall Accuracy 90.7 #101 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40-C PointNet++ Error Rate 0.236 #8 of 13 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointNet++ Mean Accuracy 75.4 #74 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointNet++ OBJ-BG (OA) 82.3 #74 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointNet++ OBJ-ONLY (OA) 84.3 #74 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointNet++ Overall Accuracy 77.9 #74 of 77 Archive leaderboard report
3D Semantic Segmentation DALES PointNet++ Model size 3.0M #5 of 9 Archive leaderboard report
3D Semantic Segmentation DALES PointNet++ Overall Accuracy 95.7 #5 of 9 Archive leaderboard report
3D Semantic Segmentation DALES PointNet++ mIoU 68.3 #5 of 9 Archive leaderboard report
3D Semantic Segmentation KITTI-360 PointNet++ Model size 3.0M #3 of 8 Archive leaderboard report
3D Semantic Segmentation KITTI-360 PointNet++ mIoU Category 58.28 #3 of 8 Archive leaderboard report
3D Semantic Segmentation KITTI-360 PointNet++ miou 35.66 #3 of 8 Archive leaderboard report
3D Semantic Segmentation STPLS3D PointNet++ mIOU 15.92 #6 of 6 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI PointNet++ test mIoU 20.1% #38 of 45 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) PointNet++ Overall Accuracy 23.05 #30 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) PointNet++ Standard Deviation 7.0 #30 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) PointNet++ Overall Accuracy 18.80 #30 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) PointNet++ Standard Deviation 7.0 #30 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) PointNet++ Overall Accuracy 38.53 #29 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) PointNet++ Standard Deviation 16.0 #29 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) PointNet++ Overall Accuracy 42.39 #29 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) PointNet++ Standard Deviation 14.2 #29 of 30 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PointNet++ (MSG) [qi2017pointnet++] Rank-1 60.23 #89 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID PointNet++ (MSG) [qi2017pointnet++] mAP 39.36 #89 of 94 Archive leaderboard report
Point Cloud Segmentation PointCloud-C PointNet++ mean Corruption Error (mCE) 1.112 #8 of 11 Archive leaderboard report
Semantic Segmentation ScanNet PointNet++ test mIoU 33.9 #32 of 45 Archive leaderboard report
Semantic Segmentation ScanNet PointNet++ val mIoU 53.5 #32 of 45 Archive leaderboard report
Semantic Segmentation ShapeNet PointNet++ Mean IoU 84.6% #5 of 5 Archive leaderboard report
Semantic Segmentation Toronto-3D L002 PointNet++ mIoU 56.5 #2 of 5 Archive leaderboard report
Semantic Segmentation Toronto-3D L002 PointNet++ oAcc 91.2 #2 of 5 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointNet++ GFLOPs 1.7 #10 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointNet++ Number of params (M) 1.5 #10 of 12 Archive leaderboard report
Supervised Only 3D Point Cloud Classification ScanObjectNN PointNet++ Overall Accuracy (PB_T50_RS) 77.9 #10 of 12 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