Papers › SO-Net: Self-Organizing Network for Point Cloud Analysis

SO-Net: Self-Organizing Network for Point Cloud Analysis

12 Mar 2018CVPR 2018 6arXiv:1803.04249archive 2025-07-28

Jiaxin Li, Ben M. Chen, Gim Hee Lee

This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net performs hierarchical feature extraction on individual points and SOM nodes, and ultimately represents the input point cloud by a single feature vector. The receptive field of the network can be systematically adjusted by conducting point-to-node k nearest neighbor search. In recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval, our proposed network demonstrates performance that is similar with or better than state-of-the-art approaches. In addition, the training speed is significantly faster than existing point cloud recognition networks because of the parallelizability and simplicity of the proposed architecture. Our code is available at the project website. https://github.com/lijx10/SO-Net

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="1803.04249")

Code

Syntology Ran 0 of 7 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run.

By repository: official repository: 5 samples from 1 repository, 0 ran; community (archive-listed): 2 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lijx10/SO-Net officialmentioned in papermentioned on GitHubpytorchMIT report
LONG-9621/SO-Net mentioned on GitHubpytorchMIT report
donnyruixu/pc-elm-ae mentioned on GitHubpytorchMIT 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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 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.

7unverified

Licence: 0 of the 7 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

compute_iou lijx10/SO-Net/models/losses.py official repository unverified MIT (permissive) · 8f4466573c6f0ffe · report
compute_iou_np_array lijx10/SO-Net/models/losses.py official repository unverified MIT (permissive) · 820fc38b598404a5 · report
knn_gather_by_indexing lijx10/SO-Net/models/operations.py official repository unverified MIT (permissive) · 501b125f7402f6d4 · report
knn_gather_wrapper lijx10/SO-Net/models/operations.py official repository unverified MIT (permissive) · 46e06b4c07842f07 · report
robust_norm lijx10/SO-Net/models/losses.py official repository unverified MIT (permissive) · 4a27074f82ccb58b · report
compute_iou LONG-9621/SO-Net/models/losses.py community (archive-listed) unverified MIT (permissive) · f1eb659f7c048f5c · report
compute_iou_np_array LONG-9621/SO-Net/models/losses.py community (archive-listed) unverified MIT (permissive) · 8dda5cb239b4da33 · report

Tasks

3D Part Segmentation3D Point Cloud Classification3D Point Cloud Linear ClassificationPoint cloud reconstructionRetrievalUnsupervised 3D Point Cloud Linear Evaluation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation IntrA SO-Net DSC (A) 88.76 #3 of 7 Archive leaderboard report
3D Part Segmentation IntrA SO-Net DSC (V) 97.09 #3 of 7 Archive leaderboard report
3D Part Segmentation IntrA SO-Net IoU (A) 81.40 #3 of 7 Archive leaderboard report
3D Part Segmentation IntrA SO-Net IoU (V) 94.46 #3 of 7 Archive leaderboard report
3D Part Segmentation ShapeNet-Part SO-Net Instance Average IoU 84.9 #57 of 67 Archive leaderboard report
3D Point Cloud Classification IntrA SO-Net F1 score (5-fold) 0.868 #9 of 12 Archive leaderboard report
3D Point Cloud Classification ModelNet40 SO-Net Overall Accuracy 90.9 #100 of 111 Archive leaderboard report
3D Point Cloud Linear Classification ModelNet40 SO-Net Overall Accuracy 87.5 #19 of 20 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

SOMSPEED

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