Papers › PointVector: A Vector Representation In Point Cloud Analysis

PointVector: A Vector Representation In Point Cloud Analysis

21 May 2022CVPR 2023 1arXiv:2205.10528archive 2025-07-28

Xin Deng, Wenyu Zhang, Qing Ding, Xinming Zhang

In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance 72.3% mIOU on the S3DIS Area 5 and 78.4% mIOU on the S3DIS (6-fold cross-validation) with only 58% model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon.

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 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (5 with no instrument failure; 5 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.

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.

guochengqian/openpoints officialpytorchMITSyntology: 11 samples, 10 ran (5 instrument-failed) · 1 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.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 5 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.

2ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
2ran
1unverified

Licence: 10 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 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 guochengqian/openpoints. “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.

guochengqian/openpoints official repository 11 samples, 10 ran (5 instrument-failed) · 1 unverified
concat_collate_fn in 7 papers dataset/build.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 65c970f35976128a · report fixture: signature datas:list/1/dict · returned dict · level recorded 2026-09-25
download_and_extract_archive in 5 papers dataset/modelnet/modelnet40_ply_2048_loader.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · b9389712035a81db · report fixture: signature url:str/0/str, path:str/0/str, md5:NoneType/0/? · returned PosixPath · level recorded 2026-09-25
farthest_point_sample in 64 papers dataset/modelnet/modelnet40_normal_resampled_loader.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
fnv_hash_vec in 14 papers dataset/data_util.py ran fingerprinted MIT (permissive) · 1a1adf2efa4893d7 · report fixture: signature arr:ndarray/2/float · returned ndarray · level recorded 2026-09-24
is_model in 24 papers models/registry.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · cd2a47ded9dd84cf · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-25
list_models in 16 papers models/registry.py ran MIT (permissive) here; the stored copy is pointer only · d14a6ca5ff9d530e · report fixture: signature filter:str/0/str, module:str/0/str, pretrained:bool/0/bool, exclude_filters:str/0/str, name_matches_cfg:bool/0/bool · returned list · level recorded 2026-09-25
load_data in 700 papers dataset/modelnet/modelnet40_ply_2048_loader.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9ed5c671b662922a · report fixture: signature data_dir:str/0/str, partition:str/0/str, url:str/0/str · returned tuple · level recorded 2026-09-25
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
dataset/modelnet/modelnet40_normal_resampled_loader.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
ravel_hash_vec in 13 papers dataset/data_util.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · afdc8ad15d9098b8 · report fixture: signature arr:ndarray/2/int · returned ndarray · level recorded 2026-09-25
register_model in 68 papers models/registry.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · e13039fb1c347452 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-25
download_url in 32 papers dataset/data_util.py unverified MIT (permissive) here; the stored copy is pointer only · 556e417290a6e1fd · report

Tasks

3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part PointVector-S(C=64) Instance Average IoU 86.9 #11 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointVector-S Mean Accuracy 91 #56 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointVector-S Overall Accuracy 93.5 #56 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointVector-S Mean Accuracy 86.2 #42 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointVector-S Overall Accuracy 87.8 #42 of 77 Archive leaderboard report
3D Semantic Segmentation OpenTrench3D PointVector-XL Model Size 24.1M #1 of 3 Archive leaderboard report
3D Semantic Segmentation OpenTrench3D PointVector-XL mAcc 84.1 #1 of 3 Archive leaderboard report
3D Semantic Segmentation OpenTrench3D PointVector-XL mIoU 76.5 #1 of 3 Archive leaderboard report
Semantic Segmentation S3DIS PointVector-XL Mean IoU 78.4 #5 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointVector-XL Params (M) 24.1 #5 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointVector-XL mAcc 86.1 #5 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointVector-XL oAcc 91.9 #5 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointVector-XL mAcc 78.1 #20 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointVector-XL mIoU 72.3 #20 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointVector-XL oAcc 91 #20 of 61 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

1x1 ConvolutionResidual Connection

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