{"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/ground-a-video-zero-shot-grounded-video","title":"Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models","arxiv_id":"2310.01107","date":"2023-10-02","proceeding":null,"authors":["Hyeonho Jeong","Jong Chul Ye"],"abstract":"Recent endeavors in video editing have showcased promising results in single-attribute editing or style transfer tasks, either by training text-to-video (T2V) models on text-video data or adopting training-free methods. However, when confronted with the complexities of multi-attribute editing scenarios, they exhibit shortcomings such as omitting or overlooking intended attribute changes, modifying the wrong elements of the input video, and failing to preserve regions of the input video that should remain intact. To address this, here we present a novel grounding-guided video-to-video translation framework called Ground-A-Video for multi-attribute video editing. Ground-A-Video attains temporally consistent multi-attribute editing of input videos in a training-free manner without aforementioned shortcomings. Central to our method is the introduction of Cross-Frame Gated Attention which incorporates groundings information into the latent representations in a temporally consistent fashion, along with Modulated Cross-Attention and optical flow guided inverted latents smoothing. Extensive experiments and applications demonstrate that Ground-A-Video's zero-shot capacity outperforms other baseline methods in terms of edit-accuracy and frame consistency. Further results and code are available at our project page (http://ground-a-video.github.io).","url_abs":"https://arxiv.org/abs/2310.01107v2","url_pdf":"https://arxiv.org/pdf/2310.01107v2.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":"ground-a-video-zero-shot-grounded-video","repo_url":"https://github.com/ground-a-video/ground-a-video","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"video-editing","task_name":"Video Editing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.01107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01107"}},"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/ground-a-video/ground-a-video","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":4,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":12,"ran":6,"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":12,"samples":[{"code_sha256_prefix":"b3e1f7172e4955ae","entry":"alpha_generator","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"inference.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/inference.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b3e1f7172e4955ae"}},{"code_sha256_prefix":"f46bcb6099334fa6","entry":"downsample_2d","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/resnet.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/resnet.py","link_basis":"harvester_set","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":"f46bcb6099334fa6"}},{"code_sha256_prefix":"d763a5bf14501d0e","entry":"get_clip_feature","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"inference.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/inference.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":"d763a5bf14501d0e"}},{"code_sha256_prefix":"6b9754bc4da711b2","entry":"prepare_magnitude_map","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/utils.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/utils.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":"6b9754bc4da711b2"}},{"code_sha256_prefix":"e49923c3510ee0bc","entry":"project","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"inference.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/inference.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e49923c3510ee0bc"}},{"code_sha256_prefix":"d3ea46d2b896a593","entry":"upfirdn2d_native","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/resnet.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/resnet.py","link_basis":"harvester_set","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":"d3ea46d2b896a593"}},{"code_sha256_prefix":"9826700aec8a8ce5","entry":"get_down_block","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/unet_3d_blocks.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/unet_3d_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":"9826700aec8a8ce5"}},{"code_sha256_prefix":"cd501a6541d20551","entry":"get_up_block","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/unet_3d_blocks.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/unet_3d_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":"cd501a6541d20551"}},{"code_sha256_prefix":"d72c9625ce8331ed","entry":"infer_optical_flow","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/utils.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/utils.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":"d72c9625ce8331ed"}},{"code_sha256_prefix":"ac172ca1a65510e6","entry":"prepare_optical_flow","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/utils.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/utils.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":"ac172ca1a65510e6"}},{"code_sha256_prefix":"31e7ed79c46ee9a9","entry":"upsample_2d","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/resnet.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/resnet.py","link_basis":"harvester_set","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":"31e7ed79c46ee9a9"}},{"code_sha256_prefix":"da94debb8019ad46","entry":"zero_module","repo":"ground-a-video/ground-a-video","repo_kind":"official","path":"controlnet/controlnet.py","file_url":"https://github.com/ground-a-video/ground-a-video/blob/HEAD/controlnet/controlnet.py","link_basis":"harvester_set","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":"da94debb8019ad46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}