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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2205.10528")

Code

Syntology Ran 1 of 11 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 11 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

guochengqian/openpoints officialpytorchMIT 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; 1 ran; 1 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
10unverified

Licence: 0 of the 11 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 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

pc_normalize guochengqian/openpoints/dataset/modelnet/modelnet40_normal_resampled_loader.py official repository ran · honoured contract fingerprinted MIT (permissive) · 4783fbece52f500e · report
concat_collate_fn guochengqian/openpoints/dataset/build.py official repository unverified MIT (permissive) · 65c970f35976128a · report
download_and_extract_archive guochengqian/openpoints/dataset/modelnet/modelnet40_ply_2048_loader.py official repository unverified MIT (permissive) · b9389712035a81db · report
download_url guochengqian/openpoints/dataset/data_util.py official repository unverified MIT (permissive) · 556e417290a6e1fd · report
farthest_point_sample guochengqian/openpoints/dataset/modelnet/modelnet40_normal_resampled_loader.py official repository unverified MIT (permissive) · f80066a00e7156a2 · report
fnv_hash_vec guochengqian/openpoints/dataset/data_util.py official repository unverified MIT (permissive) · 1a1adf2efa4893d7 · report
is_model guochengqian/openpoints/models/registry.py official repository unverified MIT (permissive) · cd2a47ded9dd84cf · report
list_models guochengqian/openpoints/models/registry.py official repository unverified MIT (permissive) · d14a6ca5ff9d530e · report
load_data guochengqian/openpoints/dataset/modelnet/modelnet40_ply_2048_loader.py official repository unverified MIT (permissive) · 9ed5c671b662922a · report
ravel_hash_vec guochengqian/openpoints/dataset/data_util.py official repository unverified MIT (permissive) · afdc8ad15d9098b8 · report
register_model guochengqian/openpoints/models/registry.py official repository unverified MIT (permissive) · e13039fb1c347452 · 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