{"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/extracting-motion-and-appearance-via-inter","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","arxiv_id":"2303.00440","date":"2023-03-01","proceeding":"CVPR 2023 1","authors":["Guozhen Zhang","Yuhan Zhu","Haonan Wang","Youxin Chen","Gangshan Wu","LiMin Wang"],"abstract":"Effectively extracting inter-frame motion and appearance information is important for video frame interpolation (VFI). Previous works either extract both types of information in a mixed way or elaborate separate modules for each type of information, which lead to representation ambiguity and low efficiency. In this paper, we propose a novel module to explicitly extract motion and appearance information via a unifying operation. Specifically, we rethink the information process in inter-frame attention and reuse its attention map for both appearance feature enhancement and motion information extraction. Furthermore, for efficient VFI, our proposed module could be seamlessly integrated into a hybrid CNN and Transformer architecture. This hybrid pipeline can alleviate the computational complexity of inter-frame attention as well as preserve detailed low-level structure information. Experimental results demonstrate that, for both fixed- and arbitrary-timestep interpolation, our method achieves state-of-the-art performance on various datasets. Meanwhile, our approach enjoys a lighter computation overhead over models with close performance. The source code and models are available at https://github.com/MCG-NJU/EMA-VFI.","url_abs":"https://arxiv.org/abs/2303.00440v2","url_pdf":"https://arxiv.org/pdf/2303.00440v2.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":"extracting-motion-and-appearance-via-inter","repo_url":"https://github.com/mcg-nju/ema-vfi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-frame-interpolation","task_name":"Video Frame Interpolation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-frame-interpolation-on-msu-video-frame","task":"Video Frame Interpolation","dataset":"MSU Video Frame Interpolation","model":"EMA-VFI","rank_in_archive_order":4,"of":24,"metrics":{"LPIPS":"0.022","MS-SSIM":"0.965","PSNR":"29.89","SSIM":"0.953","VMAF":"71.71"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-easy","task":"Video Frame Interpolation","dataset":"SNU-FILM (easy)","model":"EMA-VFI","rank_in_archive_order":7,"of":8,"metrics":{"PSNR":"39.98","SSIM":"0.9910"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-extreme","task":"Video Frame Interpolation","dataset":"SNU-FILM (extreme)","model":"EMA-VFI","rank_in_archive_order":4,"of":8,"metrics":{"PSNR":"25.69","SSIM":"0.8661"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-hard","task":"Video Frame Interpolation","dataset":"SNU-FILM (hard)","model":"EMA-VFI","rank_in_archive_order":4,"of":8,"metrics":{"PSNR":"30.94","SSIM":"0.9392"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-snu-film-medium","task":"Video Frame Interpolation","dataset":"SNU-FILM (medium)","model":"EMA-VFI","rank_in_archive_order":6,"of":8,"metrics":{"PSNR":"36.09","SSIM":"0.9801"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-ucf101-1","task":"Video Frame Interpolation","dataset":"UCF101","model":"EMA-VFI","rank_in_archive_order":1,"of":19,"metrics":{"PSNR":"35.48","SSIM":"0.9701"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-vimeo90k","task":"Video Frame Interpolation","dataset":"Vimeo90K","model":"EMA-VFI","rank_in_archive_order":2,"of":23,"metrics":{"PSNR":"36.64","SSIM":"0.9819"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps","task":"Video Frame Interpolation","dataset":"X4K1000FPS","model":"EMA-VFI","rank_in_archive_order":5,"of":20,"metrics":{"PSNR":"31.46"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-x4k1000fps-2k","task":"Video Frame Interpolation","dataset":"X4K1000FPS-2K","model":"EMA-VFI","rank_in_archive_order":2,"of":4,"metrics":{"PSNR":"32.85"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-xiph-2k","task":"Video Frame Interpolation","dataset":"Xiph-2K","model":"EMA-VFI","rank_in_archive_order":2,"of":4,"metrics":{"PSNR":"36.90","SSIM":"0.945"},"uses_additional_data":false},{"leaderboard":"/sota/video-frame-interpolation-on-xiph-4k-1","task":"Video Frame Interpolation","dataset":"Xiph-4k","model":"EMA-VFI","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"34.67","SSIM":"0.907"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.00440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00440"}},"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/mcg-nju/ema-vfi","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MCG-NJU/EMA-VFI","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_draft_wrong":2,"ran_fixture":2,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"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":"a9f0972fc8d657ae","entry":"ConvBlock","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9f0972fc8d657ae"}},{"code_sha256_prefix":"4d87dd873dd0cb76","entry":"CrossScalePatchEmbed","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d87dd873dd0cb76"}},{"code_sha256_prefix":"b5607e4cc9098c21","entry":"DWConv","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b5607e4cc9098c21"}},{"code_sha256_prefix":"5d39fa7b2acea443","entry":"InterFrameAttention","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d39fa7b2acea443"}},{"code_sha256_prefix":"49e7751169736ead","entry":"Mlp","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"49e7751169736ead"}},{"code_sha256_prefix":"bc9aa8676665e403","entry":"OverlapPatchEmbed","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc9aa8676665e403"}},{"code_sha256_prefix":"def44daa823d60b3","entry":"depad_if_needed","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"def44daa823d60b3"}},{"code_sha256_prefix":"aa39c3cb6f9a4cb6","entry":"pad_if_needed","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa39c3cb6f9a4cb6"}},{"code_sha256_prefix":"9641bf1050805151","entry":"window_partition","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9641bf1050805151"}},{"code_sha256_prefix":"4b2da073b4d351d3","entry":"window_reverse","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b2da073b4d351d3"}},{"code_sha256_prefix":"faa0a3a2edc81e48","entry":"MotionFormer","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"faa0a3a2edc81e48"}},{"code_sha256_prefix":"e3645b81274cf177","entry":"MotionFormerBlock","repo":"MCG-NJU/EMA-VFI","repo_kind":"official","path":"model/feature_extractor.py","file_url":"https://github.com/MCG-NJU/EMA-VFI/blob/HEAD/model/feature_extractor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3645b81274cf177"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}