{"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/unsupervised-deep-homography-a-fast-and","title":"Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model","arxiv_id":"1709.03966","date":"2017-09-12","proceeding":null,"authors":["Ty Nguyen","Steven W. Chen","Shreyas S. Shivakumar","Camillo J. Taylor","Vijay Kumar"],"abstract":"Homography estimation between multiple aerial images can provide relative\npose estimation for collaborative autonomous exploration and monitoring. The\nusage on a robotic system requires a fast and robust homography estimation\nalgorithm. In this study, we propose an unsupervised learning algorithm that\ntrains a Deep Convolutional Neural Network to estimate planar homographies. We\ncompare the proposed algorithm to traditional feature-based and direct methods,\nas well as a corresponding supervised learning algorithm. Our empirical results\ndemonstrate that compared to traditional approaches, the unsupervised algorithm\nachieves faster inference speed, while maintaining comparable or better\naccuracy and robustness to illumination variation. In addition, on both a\nsynthetic dataset and representative real-world aerial dataset, our\nunsupervised method has superior adaptability and performance compared to the\nsupervised deep learning method.","url_abs":"http://arxiv.org/abs/1709.03966v3","url_pdf":"http://arxiv.org/pdf/1709.03966v3.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":"unsupervised-deep-homography-a-fast-and","repo_url":"https://github.com/tynguyen/unsupervisedDeepHomographyRAL2018","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unsupervised-deep-homography-a-fast-and","repo_url":"https://github.com/JirongZhang/DeepHomography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unsupervised-deep-homography-a-fast-and","repo_url":"https://github.com/teddykoker/unsupervised-deep-homography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"homography-estimation","task_name":"Homography Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/homography-estimation-on-s-coco","task":"Homography Estimation","dataset":"S-COCO","model":"UnsupervisedHomographyNet","rank_in_archive_order":4,"of":5,"metrics":{"MACE":"2.07"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.03966","atlas_url":"https://app.syntology.ai/?focus=1709.03966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.03966"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JirongZhang/DeepHomography","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/teddykoker/unsupervised-deep-homography","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tynguyen/unsupervisedDeepHomographyRAL2018","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"04cc94da29fea6dc","entry":"str2bool","repo":"tynguyen/unsupervisedDeepHomographyRAL2018","repo_kind":"official","path":"code/homography_CNN_synthetic.py","file_url":"https://github.com/tynguyen/unsupervisedDeepHomographyRAL2018/blob/HEAD/code/homography_CNN_synthetic.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04cc94da29fea6dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}