{"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/perceptual-loss-for-robust-unsupervised","title":"Perceptual Loss for Robust Unsupervised Homography Estimation","arxiv_id":"2104.10011","date":"2021-04-20","proceeding":null,"authors":["Daniel Koguciuk","Elahe Arani","Bahram Zonooz"],"abstract":"Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit Homography Estimation (biHomE) loss for unsupervised homography estimation. biHomE minimizes the distance in the feature space between the warped image from the source viewpoint and the corresponding image from the target viewpoint. Since we use a fixed pre-trained feature extractor and the only learnable component of our framework is the homography network, we effectively decouple the homography estimation from representation learning. We use an additional photometric distortion step in the synthetic COCO dataset generation to better represent the illumination variation of the real-world scenarios. We show that biHomE achieves state-of-the-art performance on synthetic COCO dataset, which is also comparable or better compared to supervised approaches. Furthermore, the empirical results demonstrate the robustness of our approach to illumination variation compared to existing methods.","url_abs":"https://arxiv.org/abs/2104.10011v1","url_pdf":"https://arxiv.org/pdf/2104.10011v1.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":"perceptual-loss-for-robust-unsupervised","repo_url":"https://github.com/NeurAI-Lab/biHomE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dataset-generation","task_name":"Dataset Generation"},{"task_slug":"homography-estimation","task_name":"Homography Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[{"slug":"pds-coco","name":"PDS-COCO","full_name":"Photometrically Distorted Synthetic COCO"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/homography-estimation-on-pds-coco","task":"Homography Estimation","dataset":"PDS-COCO","model":"PFNet+biHomE","rank_in_archive_order":1,"of":3,"metrics":{"MACE":"2.11"},"uses_additional_data":false},{"leaderboard":"/sota/homography-estimation-on-s-coco","task":"Homography Estimation","dataset":"S-COCO","model":"PFNet+biHomE","rank_in_archive_order":2,"of":5,"metrics":{"MACE":"1.79"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.10011","atlas_url":"https://app.syntology.ai/?focus=2104.10011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10011"}},"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/NeurAI-Lab/biHomE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":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":0,"samples":[{"code_sha256_prefix":"d741eb912b24880a","entry":"all_gather","repo":"NeurAI-Lab/biHomE","repo_kind":"official","path":"src/utils/dist_util.py","file_url":"https://github.com/NeurAI-Lab/biHomE/blob/HEAD/src/utils/dist_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d741eb912b24880a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}