{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/omni-supervised-point-cloud-segmentation-via","title":"Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning","arxiv_id":"2105.10203","date":"2021-05-21","proceeding":"CVPR 2021 1","authors":["Jingyu Gong","Jiachen Xu","Xin Tan","Haichuan Song","Yanyun Qu","Yuan Xie","Lizhuang Ma"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2105.10203v1","url_pdf":"https://arxiv.org/pdf/2105.10203v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"omni-supervised-point-cloud-segmentation-via","repo_url":"https://github.com/azuki-miho/RFCR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"omni-supervised-point-cloud-segmentation-via","repo_url":"https://github.com/2023-MindSpore-1/ms-code-114","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-semantic3d","task":"Semantic Segmentation","dataset":"Semantic3D","model":"RFCR","rank_in_archive_order":2,"of":17,"metrics":{"mIoU":"77.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.10203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10203"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/azuki-miho/RFCR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"27aa4c3bde697bf7","entry":"parse_header","repo":"azuki-miho/RFCR","repo_kind":"official","path":"RandLA_Net_S3DIS/helper_ply.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/RandLA_Net_S3DIS/helper_ply.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27aa4c3bde697bf7"}},{"code_sha256_prefix":"5f8cf95da4e4af73","entry":"parse_mesh_header","repo":"azuki-miho/RFCR","repo_kind":"official","path":"RandLA_Net_S3DIS/helper_ply.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/RandLA_Net_S3DIS/helper_ply.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f8cf95da4e4af73"}},{"code_sha256_prefix":"6a88f1ae24fa26b2","entry":"bias_variable","repo":"azuki-miho/RFCR","repo_kind":"official","path":"KPConv_deform_S3DIS/models/network_blocks.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/KPConv_deform_S3DIS/models/network_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a88f1ae24fa26b2"}},{"code_sha256_prefix":"9ed4be924ecef796","entry":"conv1d","repo":"azuki-miho/RFCR","repo_kind":"official","path":"RandLA_Net_S3DIS/helper_tf_util.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/RandLA_Net_S3DIS/helper_tf_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ed4be924ecef796"}},{"code_sha256_prefix":"3ba7a15acc68a250","entry":"conv2d","repo":"azuki-miho/RFCR","repo_kind":"official","path":"RandLA_Net_S3DIS/helper_tf_util.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/RandLA_Net_S3DIS/helper_tf_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ba7a15acc68a250"}},{"code_sha256_prefix":"02f9433ac33f32b3","entry":"conv2d_transpose","repo":"azuki-miho/RFCR","repo_kind":"official","path":"RandLA_Net_S3DIS/helper_tf_util.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/RandLA_Net_S3DIS/helper_tf_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02f9433ac33f32b3"}},{"code_sha256_prefix":"4383ecd8cc0719fa","entry":"ind_max_pool","repo":"azuki-miho/RFCR","repo_kind":"official","path":"KPConv_deform_S3DIS/models/network_blocks.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/KPConv_deform_S3DIS/models/network_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4383ecd8cc0719fa"}},{"code_sha256_prefix":"1e26a8ee45f6722c","entry":"read_ply","repo":"azuki-miho/RFCR","repo_kind":"official","path":"RandLA_Net_S3DIS/helper_ply.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/RandLA_Net_S3DIS/helper_ply.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e26a8ee45f6722c"}},{"code_sha256_prefix":"5a6188c7d118c3fc","entry":"weight_variable","repo":"azuki-miho/RFCR","repo_kind":"official","path":"KPConv_deform_S3DIS/models/network_blocks.py","file_url":"https://github.com/azuki-miho/RFCR/blob/HEAD/KPConv_deform_S3DIS/models/network_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a6188c7d118c3fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}