{"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/comparing-correspondences-video-prediction","title":"Comparing Correspondences: Video Prediction with Correspondence-wise Losses","arxiv_id":"2104.09498","date":"2021-04-19","proceeding":"CVPR 2022 1","authors":["Daniel Geng","Max Hamilton","Andrew Owens"],"abstract":"Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy. In this paper, we propose a simple change to existing image similarity metrics that makes them more robust to positional errors: we match the images using optical flow, then measure the visual similarity of corresponding pixels. This change leads to crisper and more perceptually accurate predictions, and does not require modifications to the image prediction network. We apply our method to a variety of video prediction tasks, where it obtains strong performance with simple network architectures, and to the closely related task of video interpolation. Code and results are available at our webpage: https://dangeng.github.io/CorrWiseLosses","url_abs":"https://arxiv.org/abs/2104.09498v2","url_pdf":"https://arxiv.org/pdf/2104.09498v2.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":"comparing-correspondences-video-prediction","repo_url":"https://github.com/dangeng/CorrWiseLosses","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09498"}},"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/dangeng/CorrWiseLosses","reach":null}],"summary":{"ran_honours":1,"ran_fixture":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"94e47e87bb26b846","entry":"robust_l1","repo":"dangeng/CorrWiseLosses","repo_kind":"official","path":"code/corrwise/corrwise.py","file_url":"https://github.com/dangeng/CorrWiseLosses/blob/HEAD/code/corrwise/corrwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94e47e87bb26b846"}},{"code_sha256_prefix":"77bc9c9865e1da59","entry":"smoothness","repo":"dangeng/CorrWiseLosses","repo_kind":"official","path":"code/corrwise/corrwise.py","file_url":"https://github.com/dangeng/CorrWiseLosses/blob/HEAD/code/corrwise/corrwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77bc9c9865e1da59"}},{"code_sha256_prefix":"42e68b847ce157d5","entry":"sobel","repo":"dangeng/CorrWiseLosses","repo_kind":"official","path":"code/corrwise/corrwise.py","file_url":"https://github.com/dangeng/CorrWiseLosses/blob/HEAD/code/corrwise/corrwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42e68b847ce157d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}