{"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/video-diffusion-models-with-local-global","title":"Video Diffusion Models with Local-Global Context Guidance","arxiv_id":"2306.02562","date":"2023-06-05","proceeding":null,"authors":["Siyuan Yang","Lu Zhang","Yu Liu","Zhizhuo Jiang","You He"],"abstract":"Diffusion models have emerged as a powerful paradigm in video synthesis tasks including prediction, generation, and interpolation. Due to the limitation of the computational budget, existing methods usually implement conditional diffusion models with an autoregressive inference pipeline, in which the future fragment is predicted based on the distribution of adjacent past frames. However, only the conditions from a few previous frames can't capture the global temporal coherence, leading to inconsistent or even outrageous results in long-term video prediction. In this paper, we propose a Local-Global Context guided Video Diffusion model (LGC-VD) to capture multi-perception conditions for producing high-quality videos in both conditional/unconditional settings. In LGC-VD, the UNet is implemented with stacked residual blocks with self-attention units, avoiding the undesirable computational cost in 3D Conv. We construct a local-global context guidance strategy to capture the multi-perceptual embedding of the past fragment to boost the consistency of future prediction. Furthermore, we propose a two-stage training strategy to alleviate the effect of noisy frames for more stable predictions. Our experiments demonstrate that the proposed method achieves favorable performance on video prediction, interpolation, and unconditional video generation. We release code at https://github.com/exisas/LGC-VD.","url_abs":"https://arxiv.org/abs/2306.02562v1","url_pdf":"https://arxiv.org/pdf/2306.02562v1.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":"video-diffusion-models-with-local-global","repo_url":"https://github.com/exisas/lgc-vd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"future-prediction","task_name":"Future prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"unconditional-video-generation","task_name":"Unconditional Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.02562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02562"}},"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":"deterministic:regex_extraction","url":"https://github.com/exisas/LGC-VD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_violates":3,"ran":2,"unverified":10},"by_repo_kind":{"official":{"samples":17,"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":0,"samples":[{"code_sha256_prefix":"2ab2316ac6fdd869","entry":"betas_for_alpha_bar","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/model_creation.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/model_creation.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ab2316ac6fdd869"}},{"code_sha256_prefix":"d1ef6b8cb9a28a53","entry":"default","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/space_diffusion.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/space_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1ef6b8cb9a28a53"}},{"code_sha256_prefix":"fdd6aad96accd488","entry":"default_init","repo":"exisas/LGC-VD","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/model/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdd6aad96accd488"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/diffusion.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"906dac1256db387d","entry":"normalize_img","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/diffusion.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/diffusion.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"906dac1256db387d"}},{"code_sha256_prefix":"57eb67daba4326f9","entry":"unnormalize_img","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/diffusion.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/diffusion.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57eb67daba4326f9"}},{"code_sha256_prefix":"3ac11bfe0ae80195","entry":"variance_scaling","repo":"exisas/LGC-VD","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ac11bfe0ae80195"}},{"code_sha256_prefix":"7cec0870e9fb32a0","entry":"center_crop","repo":"exisas/LGC-VD","repo_kind":"official","path":"datasets/cityscapes_convert.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/datasets/cityscapes_convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7cec0870e9fb32a0"}},{"code_sha256_prefix":"540b0c5e20d1c94d","entry":"contract_inner","repo":"exisas/LGC-VD","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"540b0c5e20d1c94d"}},{"code_sha256_prefix":"78b39c6d34121c22","entry":"filename_to_num","repo":"exisas/LGC-VD","repo_kind":"official","path":"datasets/cityscapes_convert.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/datasets/cityscapes_convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78b39c6d34121c22"}},{"code_sha256_prefix":"0996aa0f716afd2d","entry":"get_beta_schedule","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/model_creation.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/model_creation.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0996aa0f716afd2d"}},{"code_sha256_prefix":"8f9c40738092ac9e","entry":"get_feats","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/evaluate.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f9c40738092ac9e"}},{"code_sha256_prefix":"1643e6831afd1067","entry":"get_fvd_feats","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/evaluate.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1643e6831afd1067"}},{"code_sha256_prefix":"0346055b4d925985","entry":"get_named_beta_schedule","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/model_creation.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/model_creation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0346055b4d925985"}},{"code_sha256_prefix":"129b5b4082e22c21","entry":"load_i3d_pretrained","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/evaluate.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"129b5b4082e22c21"}},{"code_sha256_prefix":"b8e31c4a42727fd5","entry":"read_video","repo":"exisas/LGC-VD","repo_kind":"official","path":"datasets/cityscapes_convert.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/datasets/cityscapes_convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8e31c4a42727fd5"}},{"code_sha256_prefix":"9cf6b68718b21b4c","entry":"space_timesteps","repo":"exisas/LGC-VD","repo_kind":"official","path":"video_diffusion_pytorch/space_diffusion.py","file_url":"https://github.com/exisas/LGC-VD/blob/HEAD/video_diffusion_pytorch/space_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cf6b68718b21b4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}