{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/softgroup-for-3d-instance-segmentation-on","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","arxiv_id":"2203.01509","date":"2022-03-03","proceeding":"CVPR 2022 1","authors":["Thang Vu","Kookhoi Kim","Tung M. Luu","Xuan Thanh Nguyen","Chang D. Yoo"],"abstract":"Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation such that each point is associated with a single class. However, the errors stemming from hard decision propagate into grouping that results in (1) low overlaps between the predicted instance with the ground truth and (2) substantial false positives. To address the aforementioned problems, this paper proposes a 3D instance segmentation method referred to as SoftGroup by performing bottom-up soft grouping followed by top-down refinement. SoftGroup allows each point to be associated with multiple classes to mitigate the problems stemming from semantic prediction errors and suppresses false positive instances by learning to categorize them as background. Experimental results on different datasets and multiple evaluation metrics demonstrate the efficacy of SoftGroup. Its performance surpasses the strongest prior method by a significant margin of +6.2% on the ScanNet v2 hidden test set and +6.8% on S3DIS Area 5 in terms of AP_50. SoftGroup is also fast, running at 345ms per scan with a single Titan X on ScanNet v2 dataset. The source code and trained models for both datasets are available at \\url{https://github.com/thangvubk/SoftGroup.git}.","url_abs":"https://arxiv.org/abs/2203.01509v1","url_pdf":"https://arxiv.org/pdf/2203.01509v1.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":"softgroup-for-3d-instance-segmentation-on","repo_url":"https://github.com/thangvubk/softgroup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-instance-segmentation-on-s3dis","task":"3D Instance Segmentation","dataset":"S3DIS","model":"SoftGroup","rank_in_archive_order":9,"of":21,"metrics":{"AP@50":"68.9","mAP":"54.4","mCov":"69.3","mPrec":"75.3","mRec":"69.8","mWCov":"71.7"},"uses_additional_data":true},{"leaderboard":"/sota/3d-instance-segmentation-on-stpls3d","task":"3D Instance Segmentation","dataset":"STPLS3D","model":"SoftGroup","rank_in_archive_order":6,"of":9,"metrics":{"AP":"47.3","AP25":"71.4","AP50":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-instance-segmentation-on-scannetv2","task":"3D Instance Segmentation","dataset":"ScanNet(v2)","model":"SoftGroup","rank_in_archive_order":10,"of":32,"metrics":{"mAP":"50.4","mAP @ 50":"76.1","mAP@25":"86.5"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-scannetv2","task":"3D Object Detection","dataset":"ScanNetV2","model":"SoftGroup","rank_in_archive_order":13,"of":33,"metrics":{"mAP@0.25":"71.6","mAP@0.5":"59.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.01509","atlas_url":"https://app.syntology.ai/?focus=2203.01509","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.01509"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.01509\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.01509"},"call":"get_concepts_for_paper(arxiv_id=\"2203.01509\")"}],"by_repo":[{"repo":"thangvubk/softgroup","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.09065"],"harvested_for_calls":[{"arxiv_id":"2203.09065","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09065"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09065\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7e69f31c1298a05efa016360feeee48e3f618f3dd0a798b1a2dd687bd494c861","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}