{"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/revisiting-temporal-modeling-for-video-super","title":"Revisiting Temporal Modeling for Video Super-resolution","arxiv_id":"2008.05765","date":"2020-08-13","proceeding":null,"authors":["Takashi Isobe","Fang Zhu","Xu Jia","Shengjin Wang"],"abstract":"Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR methods have been proposed, it is hard to directly compare these methods since the different loss functions and training datasets have a significant impact on the super-resolution results. In this work, we carefully study and compare three temporal modeling methods (2D CNN with early fusion, 3D CNN with slow fusion and Recurrent Neural Network) for video super-resolution. We also propose a novel Recurrent Residual Network (RRN) for efficient video super-resolution, where residual learning is utilized to stabilize the training of RNN and meanwhile to boost the super-resolution performance. Extensive experiments show that the proposed RRN is highly computational efficiency and produces temporal consistent VSR results with finer details than other temporal modeling methods. Besides, the proposed method achieves state-of-the-art results on several widely used benchmarks.","url_abs":"https://arxiv.org/abs/2008.05765v2","url_pdf":"https://arxiv.org/pdf/2008.05765v2.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":"revisiting-temporal-modeling-for-video-super","repo_url":"https://github.com/junpan19/RRN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"revisiting-temporal-modeling-for-video-super","repo_url":"https://github.com/mediatek-neuropilot/mai22-real-time-video-sr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-super-resolution","task_name":"Video Super-Resolution"}],"methods":[{"method_slug":"3d-cnn","method_name":"3D CNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-super-resolution-on-msu-vsr-benchmark","task":"Video Super-Resolution","dataset":"MSU Video Super Resolution Benchmark: Detail Restoration","model":"RRN-10L","rank_in_archive_order":15,"of":32,"metrics":{"1 - LPIPS":"0.842","ERQAv1.0":"0.627","FPS":"2.567","PSNR":"24.252","QRCRv1.0":"0.557","SSIM":"0.79","Subjective score":"5.35"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-msu-vsr-benchmark","task":"Video Super-Resolution","dataset":"MSU Video Super Resolution Benchmark: Detail Restoration","model":"RRN-5L","rank_in_archive_order":20,"of":32,"metrics":{"1 - LPIPS":"0.856","ERQAv1.0":"0.617","FPS":"2.74","PSNR":"23.786","QRCRv1.0":"0.549","SSIM":"0.789","Subjective score":"5.02"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-spmcs-4x-upscaling","task":"Video Super-Resolution","dataset":"SPMCS - 4x upscaling","model":"RRN-L","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"29.84","SSIM":"0.8690"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-udm10-4x-upscaling","task":"Video Super-Resolution","dataset":"UDM10 - 4x upscaling","model":"RRN-L","rank_in_archive_order":7,"of":7,"metrics":{"PSNR":"38.97","SSIM":"0.9534"},"uses_additional_data":false},{"leaderboard":"/sota/video-super-resolution-on-vid4-4x-upscaling-1","task":"Video Super-Resolution","dataset":"Vid4 - 4x upscaling - BD degradation","model":"RRN","rank_in_archive_order":11,"of":18,"metrics":{"PSNR":"27.69","SSIM":"0.8488"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.05765","atlas_url":"https://app.syntology.ai/?focus=2008.05765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05765"}},"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/mediatek-neuropilot/mai22-real-time-video-sr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junpan19/RRN","reach":{"status":"ok"}}],"summary":{"ran":2},"by_repo_kind":{"listed":{"samples":2,"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":"62dbff7b7b234c59","entry":"is_subclass","repo":"mediatek-neuropilot/mai22-real-time-video-sr","repo_kind":"listed","path":"util/common_util.py","file_url":"https://github.com/mediatek-neuropilot/mai22-real-time-video-sr/blob/HEAD/util/common_util.py","link_basis":"harvester_set","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":"62dbff7b7b234c59"}},{"code_sha256_prefix":"800ed13a7c7bf194","entry":"make_layer","repo":"mediatek-neuropilot/mai22-real-time-video-sr","repo_kind":"listed","path":"model/mobile_rrn.py","file_url":"https://github.com/mediatek-neuropilot/mai22-real-time-video-sr/blob/HEAD/model/mobile_rrn.py","link_basis":"harvester_set","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":"800ed13a7c7bf194"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}