{"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/cotr-correspondence-transformer-for-matching","title":"COTR: Correspondence Transformer for Matching Across Images","arxiv_id":"2103.14167","date":"2021-03-25","proceeding":"ICCV 2021 10","authors":["Wei Jiang","Eduard Trulls","Jan Hosang","Andrea Tagliasacchi","Kwang Moo Yi"],"abstract":"We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other. By doing so, one has the option to query only the points of interest and retrieve sparse correspondences, or to query all points in an image and obtain dense mappings. Importantly, in order to capture both local and global priors, and to let our model relate between image regions using the most relevant among said priors, we realize our network using a transformer. At inference time, we apply our correspondence network by recursively zooming in around the estimates, yielding a multiscale pipeline able to provide highly-accurate correspondences. Our method significantly outperforms the state of the art on both sparse and dense correspondence problems on multiple datasets and tasks, ranging from wide-baseline stereo to optical flow, without any retraining for a specific dataset. We commit to releasing data, code, and all the tools necessary to train from scratch and ensure reproducibility.","url_abs":"https://arxiv.org/abs/2103.14167v2","url_pdf":"https://arxiv.org/pdf/2103.14167v2.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":"cotr-correspondence-transformer-for-matching","repo_url":"https://github.com/ubc-vision/COTR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dense-pixel-correspondence-estimation","task_name":"Dense Pixel Correspondence Estimation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-3","task":"Dense Pixel Correspondence Estimation","dataset":"ETH3D","model":"COTR","rank_in_archive_order":1,"of":2,"metrics":{"AEPE (rate=3)":"1.66"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-3","task":"Dense Pixel Correspondence Estimation","dataset":"ETH3D","model":"COTR +Interp.","rank_in_archive_order":2,"of":2,"metrics":{"AEPE (rate=5)":"1.71"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on","task":"Dense Pixel Correspondence Estimation","dataset":"HPatches","model":"COTR","rank_in_archive_order":6,"of":8,"metrics":{"PCK-1px":"40.91","PCK-3px":"82.37","PCK-5px":"91.1","Viewpoint I AEPE":"7.75"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on","task":"Dense Pixel Correspondence Estimation","dataset":"HPatches","model":"COTR +Interp.","rank_in_archive_order":7,"of":8,"metrics":{"PCK-1px":"33.08","PCK-3px":"77.09","PCK-5px":"86.33","Viewpoint I AEPE":"7.98"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-1","task":"Dense Pixel Correspondence Estimation","dataset":"KITTI 2012","model":"COTR","rank_in_archive_order":1,"of":2,"metrics":{"Average End-Point Error":"1.28"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-1","task":"Dense Pixel Correspondence Estimation","dataset":"KITTI 2012","model":"COTR +Interp.","rank_in_archive_order":2,"of":2,"metrics":{"Average End-Point Error":"2.62"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-2","task":"Dense Pixel Correspondence Estimation","dataset":"KITTI 2015","model":"COTR","rank_in_archive_order":1,"of":2,"metrics":{"Average End-Point Error":"2.26"},"uses_additional_data":false},{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-2","task":"Dense Pixel Correspondence Estimation","dataset":"KITTI 2015","model":"COTR +Interp.","rank_in_archive_order":2,"of":2,"metrics":{"Average End-Point Error":"6.12"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2103.14167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14167"}},"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/ubc-vision/COTR","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"d996083324506d54","entry":"NerfPositionalEncoding","repo":"ubc-vision/COTR","repo_kind":"official","path":"COTR/models/cotr_model.py","file_url":"https://github.com/ubc-vision/COTR/blob/HEAD/COTR/models/cotr_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d996083324506d54"}},{"code_sha256_prefix":"6205eec2a76e0132","entry":"COTR","repo":"ubc-vision/COTR","repo_kind":"official","path":"COTR/models/cotr_model.py","file_url":"https://github.com/ubc-vision/COTR/blob/HEAD/COTR/models/cotr_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6205eec2a76e0132"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}