Papers › Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

21 May 2021CVPR 2021 1arXiv:2105.10203archive 2025-07-28

Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma

Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale supervision on intermediate layers. In this paper, we bring the first omni-scale supervision method to point cloud segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR), where target Receptive Field Component Codes (RFCCs) are designed to record categories within receptive fields for hidden units in the encoder. Then, target RFCCs will supervise the decoder to gradually infer the RFCCs in a coarse-to-fine categories reasoning manner, and finally obtain the semantic labels. Because many hidden features are inactive with tiny magnitude and make minor contributions to RFCC prediction, we propose a Feature Densification with a centrifugal potential to obtain more unambiguous features, and it is in effect equivalent to entropy regularization over features. More active features can further unleash the potential of our omni-supervision method. We embed our method into four prevailing backbones and test on three challenging benchmarks. Our method can significantly improve the backbones in all three datasets. Specifically, our method brings new state-of-the-art performances for S3DIS as well as Semantic3D and ranks the 1st in the ScanNet benchmark among all the point-based methods. Code will be publicly available at https://github.com/azuki-miho/RFCR.

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="2105.10203")

Code

Syntology Ran 2 of 9 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

azuki-miho/RFCR officialmentioned in papermentioned on GitHubtfMIT report
2023-MindSpore-1/ms-code-114 mentioned on GitHubmindspore 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

9 samples harvested; 2 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.

2ran
7unverified

Licence: 0 of the 9 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 azuki-miho/RFCR. “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.

parse_header azuki-miho/RFCR/RandLA_Net_S3DIS/helper_ply.py official repository ran MIT (permissive) · 27aa4c3bde697bf7 · report
parse_mesh_header azuki-miho/RFCR/RandLA_Net_S3DIS/helper_ply.py official repository ran MIT (permissive) · 5f8cf95da4e4af73 · report
bias_variable azuki-miho/RFCR/KPConv_deform_S3DIS/models/network_blocks.py official repository unverified MIT (permissive) · 6a88f1ae24fa26b2 · report
conv1d azuki-miho/RFCR/RandLA_Net_S3DIS/helper_tf_util.py official repository unverified MIT (permissive) · 9ed4be924ecef796 · report
conv2d azuki-miho/RFCR/RandLA_Net_S3DIS/helper_tf_util.py official repository unverified MIT (permissive) · 3ba7a15acc68a250 · report
conv2d_transpose azuki-miho/RFCR/RandLA_Net_S3DIS/helper_tf_util.py official repository unverified MIT (permissive) · 02f9433ac33f32b3 · report
ind_max_pool azuki-miho/RFCR/KPConv_deform_S3DIS/models/network_blocks.py official repository unverified MIT (permissive) · 4383ecd8cc0719fa · report
read_ply azuki-miho/RFCR/RandLA_Net_S3DIS/helper_ply.py official repository unverified MIT (permissive) · 1e26a8ee45f6722c · report
weight_variable azuki-miho/RFCR/KPConv_deform_S3DIS/models/network_blocks.py official repository unverified MIT (permissive) · 5a6188c7d118c3fc · report

Tasks

DecoderPoint Cloud SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Semantic3D RFCR mIoU 77.8% #2 of 17 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

Entropy Regularization

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