{"url":"/task/video-denoising","name":"Video Denoising","slug":"video-denoising","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":89,"papers_with_code":40,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-denoising-on-set8-sigma50","slug":"video-denoising-on-set8-sigma50","dataset":"Set8 sigma50","dataset_url":null,"rows_in_archive":9,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-davis-sigma40","slug":"video-denoising-on-davis-sigma40","dataset":"DAVIS sigma40","dataset_url":"/dataset/davis","rows_in_archive":8,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-davis-sigma50","slug":"video-denoising-on-davis-sigma50","dataset":"DAVIS sigma50","dataset_url":"/dataset/davis","rows_in_archive":8,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-set8-sigma40","slug":"video-denoising-on-set8-sigma40","dataset":"Set8 sigma40","dataset_url":null,"rows_in_archive":8,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-davis-sigma20","slug":"video-denoising-on-davis-sigma20","dataset":"DAVIS sigma20","dataset_url":"/dataset/davis","rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-davis-sigma30","slug":"video-denoising-on-davis-sigma30","dataset":"DAVIS sigma30","dataset_url":"/dataset/davis","rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-set8-sigma20","slug":"video-denoising-on-set8-sigma20","dataset":"Set8 sigma20","dataset_url":null,"rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-set8-sigma30","slug":"video-denoising-on-set8-sigma30","dataset":"Set8 sigma30","dataset_url":null,"rows_in_archive":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-davis-sigma10","slug":"video-denoising-on-davis-sigma10","dataset":"DAVIS sigma10","dataset_url":"/dataset/davis","rows_in_archive":6,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-set8-sigma10","slug":"video-denoising-on-set8-sigma10","dataset":"Set8 sigma10","dataset_url":null,"rows_in_archive":6,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-denoising-on-crvd-1","slug":"video-denoising-on-crvd-1","dataset":"CRVD","dataset_url":"/dataset/crvd","rows_in_archive":3,"metrics":["PSNR (Raw)","SSIM (Raw)","PSNR (sRBG)","SSIM (sRGB)","LPIPS (sRGB)"],"first_row_in_archive_order":{"model":"BSVD (real-time)","paper_title":"Real-time Streaming Video Denoising with Bidirectional Buffers","paper_url":"/paper/real-time-streaming-video-denoising-with","paper_date":"2022-07-14","arxiv_id":"2207.06937","code_links":[{"title":"chenyangqiqi/bsvd","url":"https://github.com/chenyangqiqi/bsvd"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/video-denoising-on-videolq","slug":"video-denoising-on-videolq","dataset":"VideoLQ","dataset_url":"/dataset/videolq","rows_in_archive":2,"metrics":["BRISQUE","NIQE","PIQE"],"first_row_in_archive_order":{"model":"ReViD","paper_title":"Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising","paper_url":"/paper/practical-real-video-denoising-with-realistic","paper_date":"2022-08-25","arxiv_id":"2208.11803","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/davis","name":"DAVIS","full_name":"Densely Annotated VIdeo Segmentation","num_papers_in_archive":734},{"url":"/dataset/crvd","name":"CRVD","full_name":"Captured Raw Video Denoising","num_papers_in_archive":26},{"url":"/dataset/videolq","name":"VideoLQ","full_name":"VideoLQ","num_papers_in_archive":16},{"url":"/dataset/i2-2000fps","name":"I2-2000FPS","full_name":"","num_papers_in_archive":2},{"url":"/dataset/sc-burst","name":"SC_burst","full_name":"Smartphone burst Dataset","num_papers_in_archive":2},{"url":"/dataset/ali","name":"SEPE 8K","full_name":"SEPE 8K","num_papers_in_archive":2},{"url":"/dataset/videezy4k","name":"Videezy4K","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":40,"tagged_in_all":89,"items":[{"url":"/paper/fastdvdnet-towards-real-time-video-denoising","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","date":"2019-07-01","arxiv_id":"1907.01361","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/recurrent-video-restoration-transformer-with","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","date":"2022-06-05","arxiv_id":"2206.02146","repositories_listed":4,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/video-enhancement-with-task-oriented-flow","title":"Video Enhancement with Task-Oriented Flow","date":"2017-11-24","arxiv_id":"1711.09078","repositories_listed":4,"syntology":null},{"url":"/paper/nerv-neural-representations-for-videos","title":"NeRV: Neural Representations for Videos","date":"2021-10-26","arxiv_id":"2110.13903","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/learning-spatial-and-spatio-temporal-pixel","title":"Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising","date":"2021-01-26","arxiv_id":"2101.10760","repositories_listed":3,"syntology":null},{"url":"/paper/modular-proximal-optimization-for","title":"Modular proximal optimization for multidimensional total-variation regularization","date":"2014-11-03","arxiv_id":"1411.0589","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/deep-video-inpainting","title":"Deep Video Inpainting","date":"2019-05-05","arxiv_id":"1905.01639","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/learning-deformable-kernels-for-image-and","title":"Learning Deformable Kernels for Image and Video Denoising","date":"2019-04-15","arxiv_id":"1904.06903","repositories_listed":2,"syntology":null},{"url":"/paper/non-local-video-denoising-by-cnn","title":"Non-Local Video Denoising by CNN","date":"2018-11-30","arxiv_id":"1811.12758","repositories_listed":2,"syntology":null},{"url":"/paper/dynamictrl-rethinking-the-basic-structure-and","title":"DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation","date":"2025-03-27","arxiv_id":"2503.21246","repositories_listed":1,"syntology":null},{"url":"/paper/spatiotemporal-blind-spot-network-with","title":"Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising","date":"2024-12-16","arxiv_id":"2412.11820","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-autoregressive-video-diffusion","title":"Progressive Autoregressive Video Diffusion Models","date":"2024-10-10","arxiv_id":"2410.08151","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/learning-truncated-causal-history-model-for","title":"Learning Truncated Causal History Model for Video Restoration","date":"2024-10-04","arxiv_id":"2410.03936","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/temporal-as-a-plugin-unsupervised-video","title":"Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers","date":"2024-09-17","arxiv_id":"2409.11256","repositories_listed":1,"syntology":null},{"url":"/paper/image-denoising-using-green-channel-prior","title":"Image Denoising Using Green Channel Prior","date":"2024-08-12","arxiv_id":"2408.05923","repositories_listed":1,"syntology":null},{"url":"/paper/idol-unified-dual-modal-latent-diffusion-for","title":"IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation","date":"2024-07-15","arxiv_id":"2407.10937","repositories_listed":1,"syntology":null},{"url":"/paper/diffir2vr-zero-zero-shot-video-restoration","title":"DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models","date":"2024-07-01","arxiv_id":"2407.01519","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/color-image-denoising-using-the-green-channel","title":"Color Image Denoising Using The Green Channel Prior","date":"2024-02-13","arxiv_id":"2402.08235","repositories_listed":1,"syntology":null},{"url":"/paper/toward-accurate-and-temporally-consistent","title":"Toward Accurate and Temporally Consistent Video Restoration from Raw Data","date":"2023-12-25","arxiv_id":"2312.16247","repositories_listed":1,"syntology":null},{"url":"/paper/learning-in-deep-factor-graphs-with-gaussian","title":"Learning in Deep Factor Graphs with Gaussian Belief Propagation","date":"2023-11-24","arxiv_id":"2311.14649","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-controllable-denoising-for-image","title":"Real-time Controllable Denoising for Image and Video","date":"2023-03-29","arxiv_id":"2303.16425","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/real-time-streaming-video-denoising-with","title":"Real-time Streaming Video Denoising with Bidirectional Buffers","date":"2022-07-14","arxiv_id":"2207.06937","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/deep-parametric-3d-filters-for-joint-video","title":"Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution","date":"2022-07-05","arxiv_id":"2207.01797","repositories_listed":1,"syntology":null},{"url":"/paper/no-attention-is-needed-grouped-spatial","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","date":"2022-06-22","arxiv_id":"2206.10810","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/unidirectional-video-denoising-by-mimicking","title":"Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Ones","date":"2022-04-12","arxiv_id":"2204.05532","repositories_listed":1,"syntology":null},{"url":"/paper/manet-improving-video-denoising-with-a-multi","title":"MANet: Improving Video Denoising with a Multi-Alignment Network","date":"2022-02-20","arxiv_id":"2202.09704","repositories_listed":1,"syntology":null},{"url":"/paper/vrt-a-video-restoration-transformer","title":"VRT: A Video Restoration Transformer","date":"2022-01-28","arxiv_id":"2201.12288","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/patch-craft-video-denoising-by-deep-modeling","title":"Patch Craft: Video Denoising by Deep Modeling and Patch Matching","date":"2021-03-25","arxiv_id":"2103.13767","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/efficient-multi-stage-video-denoising-with","title":"Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion","date":"2021-03-09","arxiv_id":"2103.05407","repositories_listed":1,"syntology":null},{"url":"/paper/mask-dngan-multi-stage-raw-video-denoising","title":"Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask","date":"2021-03-04","arxiv_id":"2103.02861","repositories_listed":1,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}