{"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/improving-transformer-based-image-matching-by","title":"Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints","arxiv_id":"2303.02885","date":"2023-03-06","proceeding":"ICCV 2023 1","authors":["Chenjie Cao","Yanwei Fu"],"abstract":"Learning robust local image feature matching is a fundamental low-level vision task, which has been widely explored in the past few years. Recently, detector-free local feature matchers based on transformers have shown promising results, which largely outperform pure Convolutional Neural Network (CNN) based ones. But correlations produced by transformer-based methods are spatially limited to the center of source views' coarse patches, because of the costly attention learning. In this work, we rethink this issue and find that such matching formulation degrades pose estimation, especially for low-resolution images. So we propose a transformer-based cascade matching model -- Cascade feature Matching TRansformer (CasMTR), to efficiently learn dense feature correlations, which allows us to choose more reliable matching pairs for the relative pose estimation. Instead of re-training a new detector, we use a simple yet effective Non-Maximum Suppression (NMS) post-process to filter keypoints through the confidence map, and largely improve the matching precision. CasMTR achieves state-of-the-art performance in indoor and outdoor pose estimation as well as visual localization. Moreover, thorough ablations show the efficacy of the proposed components and techniques.","url_abs":"https://arxiv.org/abs/2303.02885v2","url_pdf":"https://arxiv.org/pdf/2303.02885v2.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":"improving-transformer-based-image-matching-by","repo_url":"https://github.com/ewrfcas/casmtr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"visual-localization","task_name":"Visual Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.02885","atlas_url":"https://app.syntology.ai/?focus=2303.02885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02885"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ewrfcas/CasMTR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"7cdd521a480b4e75","entry":"build_optimizer","repo":"ewrfcas/CasMTR","repo_kind":"official","path":"src/lightning/lightning_cascade_refine.py","file_url":"https://github.com/ewrfcas/CasMTR/blob/HEAD/src/lightning/lightning_cascade_refine.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7cdd521a480b4e75"}},{"code_sha256_prefix":"be0730ce3a1dd5b7","entry":"get_lr_schedule_with_stepwise_cosine","repo":"ewrfcas/CasMTR","repo_kind":"official","path":"src/lightning/lightning_cascade.py","file_url":"https://github.com/ewrfcas/CasMTR/blob/HEAD/src/lightning/lightning_cascade.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be0730ce3a1dd5b7"}},{"code_sha256_prefix":"8d6f91e0320aadfc","entry":"get_match_config","repo":"ewrfcas/CasMTR","repo_kind":"official","path":"src/model/cascade_model_stage3.py","file_url":"https://github.com/ewrfcas/CasMTR/blob/HEAD/src/model/cascade_model_stage3.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d6f91e0320aadfc"}},{"code_sha256_prefix":"bf0063a9e04d436b","entry":"set_stage_mask","repo":"ewrfcas/CasMTR","repo_kind":"official","path":"src/model/cascade_model_stage3.py","file_url":"https://github.com/ewrfcas/CasMTR/blob/HEAD/src/model/cascade_model_stage3.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bf0063a9e04d436b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}