{"url":"/task/video-inpainting","name":"Video Inpainting","slug":"video-inpainting","description_markdown":"The goal of **Video Inpainting** is to fill in missing regions of a given video sequence with contents that are both spatially and temporally coherent. Video Inpainting, also known as video completion, has many real-world applications such as undesired object removal and video restoration.\r\n\r\n\r\n<span class=\"description-source\">Source: [Deep Flow-Guided Video Inpainting ](https://arxiv.org/abs/1905.02884)</span>","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":130,"papers_with_code":59,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":15,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-inpainting-on-davis","slug":"video-inpainting-on-davis","dataset":"DAVIS","dataset_url":"/dataset/davis","rows_in_archive":11,"metrics":["PSNR","SSIM","VFID","Ewarp","LPIPS (object)","LPIPS (square)","PNSR (object)","SSIM (object)","SSIM (square)"],"first_row_in_archive_order":{"model":"DMT","paper_title":"Deficiency-Aware Masked Transformer for Video Inpainting","paper_url":"/paper/deficiency-aware-masked-transformer-for-video","paper_date":"2023-07-17","arxiv_id":"2307.08629","code_links":[{"title":"yeates/dmt","url":"https://github.com/yeates/dmt"}],"syntology":null}},{"leaderboard":"/sota/video-inpainting-on-youtube-vos","slug":"video-inpainting-on-youtube-vos","dataset":"YouTube-VOS 2018","dataset_url":"/dataset/youtube-vos","rows_in_archive":10,"metrics":["PSNR","SSIM","VFID","Ewarp"],"first_row_in_archive_order":{"model":"ProPainter","paper_title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","paper_url":"/paper/propainter-improving-propagation-and","paper_date":"2023-09-07","arxiv_id":"2309.03897","code_links":[{"title":"sczhou/propainter","url":"https://github.com/sczhou/propainter"},{"title":"osmr/propainter","url":"https://github.com/osmr/propainter"},{"title":"osmr/pytorchcv","url":"https://github.com/osmr/pytorchcv"}],"syntology":{"n":34,"n_ran":20,"n_unverified":14,"n_pointer_only":16}}},{"leaderboard":"/sota/video-inpainting-on-hqvi-240p","slug":"video-inpainting-on-hqvi-240p","dataset":"HQVI (240p)","dataset_url":null,"rows_in_archive":7,"metrics":["LPIPS","VFID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"RGVI","paper_title":"Elevating Flow-Guided Video Inpainting with Reference Generation","paper_url":"/paper/elevating-flow-guided-video-inpainting-with","paper_date":"2024-12-12","arxiv_id":"2412.08975","code_links":[{"title":"suhwan-cho/RGVI","url":"https://github.com/suhwan-cho/RGVI"}],"syntology":null}},{"leaderboard":"/sota/video-inpainting-on-hqvi-480p","slug":"video-inpainting-on-hqvi-480p","dataset":"HQVI (480p)","dataset_url":null,"rows_in_archive":4,"metrics":["LPIPS","VFID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"RGVI","paper_title":"Elevating Flow-Guided Video Inpainting with Reference Generation","paper_url":"/paper/elevating-flow-guided-video-inpainting-with","paper_date":"2024-12-12","arxiv_id":"2412.08975","code_links":[{"title":"suhwan-cho/RGVI","url":"https://github.com/suhwan-cho/RGVI"}],"syntology":null}},{"leaderboard":"/sota/video-inpainting-on-hqvi-2k","slug":"video-inpainting-on-hqvi-2k","dataset":"HQVI (2K)","dataset_url":null,"rows_in_archive":2,"metrics":["LPIPS","VFID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"RGVI","paper_title":"Elevating Flow-Guided Video Inpainting with Reference Generation","paper_url":"/paper/elevating-flow-guided-video-inpainting-with","paper_date":"2024-12-12","arxiv_id":"2412.08975","code_links":[{"title":"suhwan-cho/RGVI","url":"https://github.com/suhwan-cho/RGVI"}],"syntology":null}},{"leaderboard":"/sota/video-inpainting-on-youtube-vos-1","slug":"video-inpainting-on-youtube-vos-1","dataset":"YouTube-VOS","dataset_url":"/dataset/youtube-vos","rows_in_archive":2,"metrics":["LPIPS","PSNR","PSNR (square)","SSIM"],"first_row_in_archive_order":{"model":"FGT++","paper_title":"Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting","paper_url":"/paper/exploiting-optical-flow-guidance-for","paper_date":"2023-01-24","arxiv_id":"2301.10048","code_links":[{"title":"hitachinsk/fgt","url":"https://github.com/hitachinsk/fgt"},{"title":"hitachinsk/isvi","url":"https://github.com/hitachinsk/isvi"}],"syntology":null}},{"leaderboard":"/sota/video-inpainting-on-how2sign","slug":"video-inpainting-on-how2sign","dataset":"How2Sign","dataset_url":"/dataset/how2sign","rows_in_archive":1,"metrics":["L1 error"],"first_row_in_archive_order":{"model":"INR-V","paper_title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","paper_url":"/paper/inr-v-a-continuous-representation-space-for","paper_date":"2022-10-29","arxiv_id":"2210.16579","code_links":[{"title":"bipashasen/INRV","url":"https://github.com/bipashasen/INRV"},{"title":"MindSpore-scientific-2/code-5","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"}],"syntology":null}}],"datasets":[{"url":"/dataset/davis","name":"DAVIS","full_name":"Densely Annotated VIdeo Segmentation","num_papers_in_archive":734},{"url":"/dataset/youtube-vos","name":"YouTube-VOS 2018","full_name":"Youtube Video Object Segmentation","num_papers_in_archive":203},{"url":"/dataset/how2sign","name":"How2Sign","full_name":"A Large-scale Multimodal Dataset for Continuous American Sign Language","num_papers_in_archive":44},{"url":"/dataset/egohos","name":"EgoHOS","full_name":"Fine-Grained Egocentric Hand-Object Segmentation Dataset","num_papers_in_archive":9},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/fvi","name":"FVI","full_name":"Free-form Video Inpainting","num_papers_in_archive":8},{"url":"/dataset/kitti360-ex","name":"KITTI360-EX","full_name":"","num_papers_in_archive":7},{"url":"/dataset/devil","name":"DEVIL","full_name":"Diagnostic Evaluation of Video Inpainting on Landscapes","num_papers_in_archive":3},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/apolloscape-inpainting","name":"Apolloscape Inpainting","full_name":"","num_papers_in_archive":1},{"url":"/dataset/videoremoval4k","name":"VideoRemoval4K","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vpbench","name":"VPBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vpdata","name":"VPData","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dreaming-inpainting-dataset","name":"DREAMING Inpainting Dataset","full_name":"Diminished Reality for Emerging Applications in Medicine through Inpainting Dataset","num_papers_in_archive":0},{"url":"/dataset/wrv","name":"WRV","full_name":"Wire-removal Dataset","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/3d","name":"3D"}],"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":59,"tagged_in_all":130,"items":[{"url":"/paper/propainter-improving-propagation-and","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","date":"2023-09-07","arxiv_id":"2309.03897","repositories_listed":3,"syntology":{"n":34,"n_ran":20,"n_unverified":14,"n_pointer_only":16}},{"url":"/paper/flowlens-seeing-beyond-the-fov-via-flow","title":"Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer","date":"2022-11-21","arxiv_id":"2211.11293","repositories_listed":3,"syntology":null},{"url":"/paper/inr-v-a-continuous-representation-space-for","title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","date":"2022-10-29","arxiv_id":"2210.16579","repositories_listed":3,"syntology":null},{"url":"/paper/exploiting-optical-flow-guidance-for","title":"Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting","date":"2023-01-24","arxiv_id":"2301.10048","repositories_listed":2,"syntology":null},{"url":"/paper/towards-an-end-to-end-framework-for-flow","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","date":"2022-04-06","arxiv_id":"2204.02663","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/learning-joint-spatial-temporal","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","date":"2020-07-20","arxiv_id":"2007.10247","repositories_listed":2,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/dvi-depth-guided-video-inpainting-for","title":"DVI: Depth Guided Video Inpainting for Autonomous Driving","date":"2020-07-17","arxiv_id":"2007.08854","repositories_listed":2,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/learnable-gated-temporal-shift-module-for","title":"Learnable Gated Temporal Shift Module for Deep Video Inpainting","date":"2019-07-02","arxiv_id":"1907.01131","repositories_listed":2,"syntology":null},{"url":"/paper/deep-flow-guided-video-inpainting","title":"Deep Flow-Guided Video Inpainting","date":"2019-05-08","arxiv_id":"1905.02884","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"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/free-form-video-inpainting-with-3d-gated","title":"Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN","date":"2019-04-23","arxiv_id":"1904.10247","repositories_listed":2,"syntology":null},{"url":"/paper/swapanyone-consistent-and-realistic-video","title":"SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video","date":"2025-03-12","arxiv_id":"2503.09154","repositories_listed":1,"syntology":null},{"url":"/paper/videopainter-any-length-video-inpainting-and","title":"VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control","date":"2025-03-07","arxiv_id":"2503.05639","repositories_listed":1,"syntology":null},{"url":"/paper/diffueraser-a-diffusion-model-for-video","title":"DiffuEraser: A Diffusion Model for Video Inpainting","date":"2025-01-17","arxiv_id":"2501.10018","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/elevating-flow-guided-video-inpainting-with","title":"Elevating Flow-Guided Video Inpainting with Reference Generation","date":"2024-12-12","arxiv_id":"2412.08975","repositories_listed":1,"syntology":null},{"url":"/paper/advanced-video-inpainting-using-optical-flow","title":"Advanced Video Inpainting Using Optical Flow-Guided Efficient Diffusion","date":"2024-12-01","arxiv_id":"2412.00857","repositories_listed":1,"syntology":null},{"url":"/paper/motionaura-generating-high-quality-and-motion","title":"MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion","date":"2024-10-10","arxiv_id":"2410.07659","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/replace-anyone-in-videos","title":"Replace Anyone in Videos","date":"2024-09-30","arxiv_id":"2409.19911","repositories_listed":1,"syntology":null},{"url":"/paper/stereocrafter-diffusion-based-generation-of","title":"StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos","date":"2024-09-11","arxiv_id":"2409.07447","repositories_listed":1,"syntology":null},{"url":"/paper/depth-aware-endoscopic-video-inpainting","title":"Depth-Aware Endoscopic Video Inpainting","date":"2024-07-02","arxiv_id":"2407.02675","repositories_listed":1,"syntology":null},{"url":"/paper/video-inpainting-localization-with","title":"Video Inpainting Localization with Contrastive Learning","date":"2024-06-25","arxiv_id":"2406.17628","repositories_listed":1,"syntology":null},{"url":"/paper/trusted-video-inpainting-localization-via","title":"Trusted Video Inpainting Localization via Deep Attentive Noise Learning","date":"2024-06-19","arxiv_id":"2406.13576","repositories_listed":1,"syntology":null},{"url":"/paper/raformer-redundancy-aware-transformer-for","title":"Raformer: Redundancy-Aware Transformer for Video Wire Inpainting","date":"2024-04-24","arxiv_id":"2404.15802","repositories_listed":1,"syntology":null},{"url":"/paper/vq-nerv-a-vector-quantized-neural","title":"VQ-NeRV: A Vector Quantized Neural Representation for Videos","date":"2024-03-19","arxiv_id":"2403.12401","repositories_listed":1,"syntology":null},{"url":"/paper/cococo-improving-text-guided-video-inpainting","title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","date":"2024-03-18","arxiv_id":"2403.12035","repositories_listed":1,"syntology":null},{"url":"/paper/expression-aware-video-inpainting-for-hmd","title":"Expression-aware video inpainting for HMD removal in XR applications","date":"2024-01-25","arxiv_id":"2401.14136","repositories_listed":1,"syntology":null},{"url":"/paper/lumiere-a-space-time-diffusion-model-for","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","date":"2024-01-23","arxiv_id":"2401.12945","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/towards-language-driven-video-inpainting-via","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","date":"2024-01-18","arxiv_id":"2401.10226","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/avid-any-length-video-inpainting-with","title":"AVID: Any-Length Video Inpainting with Diffusion Model","date":"2023-12-06","arxiv_id":"2312.03816","repositories_listed":1,"syntology":null},{"url":"/paper/bivdiff-a-training-free-framework-for-general","title":"BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models","date":"2023-12-05","arxiv_id":"2312.02813","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}}],"syntology_records":11,"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"}}