{"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/usip-unsupervised-stable-interest-point","title":"USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds","arxiv_id":"1904.00229","date":"2019-03-30","proceeding":"ICCV 2019 10","authors":["Jiaxin Li","Gim Hee Lee"],"abstract":"In this paper, we propose the USIP detector: an Unsupervised Stable Interest\nPoint detector that can detect highly repeatable and accurately localized\nkeypoints from 3D point clouds under arbitrary transformations without the need\nfor any ground truth training data. Our USIP detector consists of a feature\nproposal network that learns stable keypoints from input 3D point clouds and\ntheir respective transformed pairs from randomly generated transformations. We\nprovide degeneracy analysis of our USIP detector and suggest solutions to\nprevent it. We encourage high repeatability and accurate localization of the\nkeypoints with a probabilistic chamfer loss that minimizes the distances\nbetween the detected keypoints from the training point cloud pairs. Extensive\nexperimental results of repeatability tests on several simulated and real-world\n3D point cloud datasets from Lidar, RGB-D and CAD models show that our USIP\ndetector significantly outperforms existing hand-crafted and deep\nlearning-based 3D keypoint detectors. Our code is available at the project\nwebsite. https://github.com/lijx10/USIP","url_abs":"http://arxiv.org/abs/1904.00229v1","url_pdf":"http://arxiv.org/pdf/1904.00229v1.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":"usip-unsupervised-stable-interest-point","repo_url":"https://github.com/lijx10/USIP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"interest-point-detection","task_name":"Interest Point Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00229"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lijx10/USIP","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"72842c648d9fe8fa","entry":"model_state_dict_convert_auto","repo":"lijx10/USIP","repo_kind":"official","path":"kitti/train_detector.py","file_url":"https://github.com/lijx10/USIP/blob/HEAD/kitti/train_detector.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"72842c648d9fe8fa"}},{"code_sha256_prefix":"1cea3f00eb210c8b","entry":"model_state_dict_parallel_convert","repo":"lijx10/USIP","repo_kind":"official","path":"kitti/train_detector.py","file_url":"https://github.com/lijx10/USIP/blob/HEAD/kitti/train_detector.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1cea3f00eb210c8b"}},{"code_sha256_prefix":"9cd470c2cf27c6f8","entry":"random_string_generator","repo":"lijx10/USIP","repo_kind":"official","path":"evaluation/save_keypoints.py","file_url":"https://github.com/lijx10/USIP/blob/HEAD/evaluation/save_keypoints.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9cd470c2cf27c6f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}