{"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/matchable-image-retrieval-by-learning-from","title":"Matchable Image Retrieval by Learning from Surface Reconstruction","arxiv_id":"1811.10343","date":"2018-11-26","proceeding":null,"authors":["Tianwei Shen","Zixin Luo","Lei Zhou","Runze Zhang","Siyu Zhu","Tian Fang","Long Quan"],"abstract":"Convolutional Neural Networks (CNNs) have achieved superior performance on\nobject image retrieval, while Bag-of-Words (BoW) models with handcrafted local\nfeatures still dominate the retrieval of overlapping images in 3D\nreconstruction. In this paper, we narrow down this gap by presenting an\nefficient CNN-based method to retrieve images with overlaps, which we refer to\nas the matchable image retrieval problem. Different from previous methods that\ngenerates training data based on sparse reconstruction, we create a large-scale\nimage database with rich 3D geometrics and exploit information from surface\nreconstruction to obtain fine-grained training data. We propose a batched\ntriplet-based loss function combined with mesh re-projection to effectively\nlearn the CNN representation. The proposed method significantly accelerates the\nimage retrieval process in 3D reconstruction and outperforms the\nstate-of-the-art CNN-based and BoW methods for matchable image retrieval. The\ncode and data are available at https://github.com/hlzz/mirror.","url_abs":"http://arxiv.org/abs/1811.10343v2","url_pdf":"http://arxiv.org/pdf/1811.10343v2.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":"matchable-image-retrieval-by-learning-from","repo_url":"https://github.com/hlzz/mirror","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10343"}},"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/hlzz/mirror","reach":null}],"summary":{"ran_fixture":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":"3c9e01b7430aa766","entry":"normalize","repo":"hlzz/mirror","repo_kind":"official","path":"retrieval/deep_query.py","file_url":"https://github.com/hlzz/mirror/blob/HEAD/retrieval/deep_query.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c9e01b7430aa766"}},{"code_sha256_prefix":"e42a29279f687008","entry":"simple_query_expansion","repo":"hlzz/mirror","repo_kind":"official","path":"retrieval/deep_query.py","file_url":"https://github.com/hlzz/mirror/blob/HEAD/retrieval/deep_query.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":"e42a29279f687008"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}