{"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/towards-language-driven-video-inpainting-via","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","arxiv_id":"2401.10226","date":"2024-01-18","proceeding":"CVPR 2024 1","authors":["Jianzong Wu","Xiangtai Li","Chenyang Si","Shangchen Zhou","Jingkang Yang","Jiangning Zhang","Yining Li","Kai Chen","Yunhai Tong","Ziwei Liu","Chen Change Loy"],"abstract":"We introduce a new task -- language-driven video inpainting, which uses natural language instructions to guide the inpainting process. This approach overcomes the limitations of traditional video inpainting methods that depend on manually labeled binary masks, a process often tedious and labor-intensive. We present the Remove Objects from Videos by Instructions (ROVI) dataset, containing 5,650 videos and 9,091 inpainting results, to support training and evaluation for this task. We also propose a novel diffusion-based language-driven video inpainting framework, the first end-to-end baseline for this task, integrating Multimodal Large Language Models to understand and execute complex language-based inpainting requests effectively. Our comprehensive results showcase the dataset's versatility and the model's effectiveness in various language-instructed inpainting scenarios. We will make datasets, code, and models publicly available.","url_abs":"https://arxiv.org/abs/2401.10226v2","url_pdf":"https://arxiv.org/pdf/2401.10226v2.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":"towards-language-driven-video-inpainting-via","repo_url":"https://github.com/jianzongwu/language-driven-video-inpainting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-inpainting","task_name":"Video Inpainting"}],"methods":[{"method_slug":"pixel-prediction","method_name":"Inpainting"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.10226","atlas_url":"https://app.syntology.ai/?focus=2401.10226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10226"}},"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/jianzongwu/language-driven-video-inpainting","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":10,"samples":[{"code_sha256_prefix":"2eb56328ee222a96","entry":"create_1d_absolute_sin_cos_embedding","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/models/utils.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2eb56328ee222a96"}},{"code_sha256_prefix":"d38dd5fa6084deeb","entry":"get_cosine_scheduler","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/util.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d38dd5fa6084deeb"}},{"code_sha256_prefix":"a37c74cff74be0d0","entry":"get_mask_loss_weight_scale_quadratic","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/util.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a37c74cff74be0d0"}},{"code_sha256_prefix":"5ca301a24eda4247","entry":"get_unet_constant_deocder_cosine_scheduler","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/util.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ca301a24eda4247"}},{"code_sha256_prefix":"1b457a7bd99a3de9","entry":"inflated_interpolate_3d","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/models/mask_decoder.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/models/mask_decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b457a7bd99a3de9"}},{"code_sha256_prefix":"a612419f9fdb01ba","entry":"load_video","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"inference_interactive.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/inference_interactive.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a612419f9fdb01ba"}},{"code_sha256_prefix":"0b8d172f39477909","entry":"transform_first_frame","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"inference_interactive.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/inference_interactive.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b8d172f39477909"}},{"code_sha256_prefix":"f6cbe1f5a30557f3","entry":"get_down_block","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/models/unet_blocks.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/models/unet_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6cbe1f5a30557f3"}},{"code_sha256_prefix":"45965320324d4cff","entry":"get_mask_decoder","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/models/mask_decoder.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/models/mask_decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45965320324d4cff"}},{"code_sha256_prefix":"b371191d08e93feb","entry":"get_up_block","repo":"jianzongwu/Language-Driven-Video-Inpainting","repo_kind":"official","path":"rovi/models/unet_blocks.py","file_url":"https://github.com/jianzongwu/Language-Driven-Video-Inpainting/blob/HEAD/rovi/models/unet_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b371191d08e93feb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}