{"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/bootstrap-your-own-correspondences","title":"Bootstrap Your Own Correspondences","arxiv_id":"2106.00677","date":"2021-06-01","proceeding":"ICCV 2021 10","authors":["Mohamed El Banani","Justin Johnson"],"abstract":"Geometric feature extraction is a crucial component of point cloud registration pipelines. Recent work has demonstrated how supervised learning can be leveraged to learn better and more compact 3D features. However, those approaches' reliance on ground-truth annotation limits their scalability. We propose BYOC: a self-supervised approach that learns visual and geometric features from RGB-D video without relying on ground-truth pose or correspondence. Our key observation is that randomly-initialized CNNs readily provide us with good correspondences; allowing us to bootstrap the learning of both visual and geometric features. Our approach combines classic ideas from point cloud registration with more recent representation learning approaches. We evaluate our approach on indoor scene datasets and find that our method outperforms traditional and learned descriptors, while being competitive with current state-of-the-art supervised approaches.","url_abs":"https://arxiv.org/abs/2106.00677v1","url_pdf":"https://arxiv.org/pdf/2106.00677v1.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":[],"tasks":[{"task_slug":"point-cloud-registration","task_name":"Point Cloud Registration"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.00677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00677"}},"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/mbanani/byoc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"found_in_text":{"samples":9,"ran":0,"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":"2508b020295d7823","entry":"align","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/models/alignment.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/models/alignment.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":"2508b020295d7823"}},{"code_sha256_prefix":"63c1df24808bc1ae","entry":"build_dataset","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/datasets/builder.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/datasets/builder.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":"63c1df24808bc1ae"}},{"code_sha256_prefix":"fca9a8934386530f","entry":"build_model","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/models/builder.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/models/builder.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":"fca9a8934386530f"}},{"code_sha256_prefix":"1c65d2c53b3b926b","entry":"calculate_ratio_test","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/models/correspondence.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/models/correspondence.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":"1c65d2c53b3b926b"}},{"code_sha256_prefix":"c65a0c6c9123e7f5","entry":"evaluate_3d_correspondances","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/utils/metrics.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/utils/metrics.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":"c65a0c6c9123e7f5"}},{"code_sha256_prefix":"7125de3e5cc61b12","entry":"evaluate_correspondances","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/utils/metrics.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/utils/metrics.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":"7125de3e5cc61b12"}},{"code_sha256_prefix":"613a3a3a21f9a4dd","entry":"get_topk_matches","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/models/correspondence.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/models/correspondence.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":"613a3a3a21f9a4dd"}},{"code_sha256_prefix":"56c4a83a8b6469be","entry":"paired_svd","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/models/alignment.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/models/alignment.py","link_basis":"plan_row","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":"56c4a83a8b6469be"}},{"code_sha256_prefix":"5ddb3c71c6feae1f","entry":"randomized_weighted_procrustes","repo":"mbanani/byoc","repo_kind":"found_in_text","path":"byoc/models/alignment.py","file_url":"https://github.com/mbanani/byoc/blob/HEAD/byoc/models/alignment.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":"5ddb3c71c6feae1f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}