{"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/learning-spatial-transform-for-video-frame","title":"AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation","arxiv_id":"1907.10244","date":"2019-07-24","proceeding":"CVPR 2020 6","authors":["Hyeongmin Lee","Taeoh Kim","Tae-young Chung","Daehyun Pak","Yuseok Ban","Sangyoun Lee"],"abstract":"Video frame interpolation is one of the most challenging tasks in video processing research. Recently, many studies based on deep learning have been suggested. Most of these methods focus on finding locations with useful information to estimate each output pixel using their own frame warping operations. However, many of them have Degrees of Freedom (DoF) limitations and fail to deal with the complex motions found in real world videos. To solve this problem, we propose a new warping module named Adaptive Collaboration of Flows (AdaCoF). Our method estimates both kernel weights and offset vectors for each target pixel to synthesize the output frame. AdaCoF is one of the most generalized warping modules compared to other approaches, and covers most of them as special cases of it. Therefore, it can deal with a significantly wide domain of complex motions. To further improve our framework and synthesize more realistic outputs, we introduce dual-frame adversarial loss which is applicable only to video frame interpolation tasks. The experimental results show that our method outperforms the state-of-the-art methods for both fixed training set environments and the Middlebury benchmark.","url_abs":"https://arxiv.org/abs/1907.10244v3","url_pdf":"https://arxiv.org/pdf/1907.10244v3.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":"learning-spatial-transform-for-video-frame","repo_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-frame-interpolation-on-msu-video-frame","task":"Video Frame Interpolation","dataset":"MSU Video Frame Interpolation","model":"AdaCoF_f","rank_in_archive_order":20,"of":24,"metrics":{"LPIPS":"0.058","MS-SSIM":"0.913","PSNR":"24.99","SSIM":"0.903","VMAF":"60.19"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-msu-video-frame","task":"Video Frame Interpolation","dataset":"MSU Video Frame Interpolation","model":"AdaCoF","rank_in_archive_order":24,"of":24,"metrics":{"LPIPS":"0.692","MS-SSIM":"0.883","PSNR":"23.17","SSIM":"0.891","VMAF":"58.29"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps","task":"Video Frame Interpolation","dataset":"X4K1000FPS","model":"AdaCoF_f","rank_in_archive_order":17,"of":20,"metrics":{"PSNR":"25.81","SSIM":"0.772","tOF":"6.42"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps","task":"Video Frame Interpolation","dataset":"X4K1000FPS","model":"AdaCoF","rank_in_archive_order":20,"of":20,"metrics":{"PSNR":"23.90","SSIM":"0.727","tOF":"6.89"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.10244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10244"}},"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/HyeongminLEE/AdaCoF-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"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":"9e8e56135365289e","entry":"CharbonnierFunc","repo":"HyeongminLEE/AdaCoF-pytorch","repo_kind":"official","path":"utility.py","file_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch/blob/HEAD/utility.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e8e56135365289e"}},{"code_sha256_prefix":"989c91edb537cd8f","entry":"to_variable","repo":"HyeongminLEE/AdaCoF-pytorch","repo_kind":"official","path":"interpolate_twoframe.py","file_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch/blob/HEAD/interpolate_twoframe.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"989c91edb537cd8f"}},{"code_sha256_prefix":"c11a926b49696f09","entry":"cointoss","repo":"HyeongminLEE/AdaCoF-pytorch","repo_kind":"official","path":"datareader.py","file_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch/blob/HEAD/datareader.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":"c11a926b49696f09"}},{"code_sha256_prefix":"ab4f2d6ba82b40b0","entry":"cupy_kernel","repo":"HyeongminLEE/AdaCoF-pytorch","repo_kind":"official","path":"cupy_module/adacof.py","file_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch/blob/HEAD/cupy_module/adacof.py","link_basis":"harvester_set","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":"ab4f2d6ba82b40b0"}},{"code_sha256_prefix":"35612f45302f599e","entry":"make_optimizer","repo":"HyeongminLEE/AdaCoF-pytorch","repo_kind":"official","path":"utility.py","file_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch/blob/HEAD/utility.py","link_basis":"harvester_set","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":"35612f45302f599e"}},{"code_sha256_prefix":"79544811771ac207","entry":"make_scheduler","repo":"HyeongminLEE/AdaCoF-pytorch","repo_kind":"official","path":"utility.py","file_url":"https://github.com/HyeongminLEE/AdaCoF-pytorch/blob/HEAD/utility.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":"79544811771ac207"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}