Papers › Video Diffusion Models with Local-Global Context Guidance

Video Diffusion Models with Local-Global Context Guidance

5 Jun 2023arXiv:2306.02562archive 2025-07-28

Siyuan Yang, Lu Zhang, Yu Liu, Zhizhuo Jiang, You He

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.02562")

Code

Syntology Ran 7 of 17 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · violated contract; 2 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

exisas/lgc-vd officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 7 ran; 2 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
3ran · violated contract
2ran
10unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from exisas/LGC-VD. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

betas_for_alpha_bar exisas/LGC-VD/video_diffusion_pytorch/model_creation.py official repository ran · honoured contract MIT (permissive) · 2ab2316ac6fdd869 · report
default exisas/LGC-VD/video_diffusion_pytorch/space_diffusion.py official repository ran · violated contract MIT (permissive) · d1ef6b8cb9a28a53 · report
default_init exisas/LGC-VD/model/utils.py official repository ran MIT (permissive) · fdd6aad96accd488 · report
exists exisas/LGC-VD/video_diffusion_pytorch/diffusion.py official repository ran · violated contract MIT (permissive) · 608e364a9d2376a3 · report
normalize_img exisas/LGC-VD/video_diffusion_pytorch/diffusion.py official repository ran · honoured contract fingerprinted MIT (permissive) · 906dac1256db387d · report
unnormalize_img exisas/LGC-VD/video_diffusion_pytorch/diffusion.py official repository ran · violated contract fingerprinted MIT (permissive) · 57eb67daba4326f9 · report
variance_scaling exisas/LGC-VD/model/utils.py official repository ran MIT (permissive) · 3ac11bfe0ae80195 · report
center_crop exisas/LGC-VD/datasets/cityscapes_convert.py official repository unverified MIT (permissive) · 7cec0870e9fb32a0 · report
contract_inner exisas/LGC-VD/model/utils.py official repository unverified MIT (permissive) · 540b0c5e20d1c94d · report
filename_to_num exisas/LGC-VD/datasets/cityscapes_convert.py official repository unverified MIT (permissive) · 78b39c6d34121c22 · report
get_beta_schedule exisas/LGC-VD/video_diffusion_pytorch/model_creation.py official repository unverified MIT (permissive) · 0996aa0f716afd2d · report
get_feats exisas/LGC-VD/video_diffusion_pytorch/evaluate.py official repository unverified MIT (permissive) · 8f9c40738092ac9e · report
get_fvd_feats exisas/LGC-VD/video_diffusion_pytorch/evaluate.py official repository unverified MIT (permissive) · 1643e6831afd1067 · report
get_named_beta_schedule exisas/LGC-VD/video_diffusion_pytorch/model_creation.py official repository unverified MIT (permissive) · 0346055b4d925985 · report
load_i3d_pretrained exisas/LGC-VD/video_diffusion_pytorch/evaluate.py official repository unverified MIT (permissive) · 129b5b4082e22c21 · report
read_video exisas/LGC-VD/datasets/cityscapes_convert.py official repository unverified MIT (permissive) · b8e31c4a42727fd5 · report
space_timesteps exisas/LGC-VD/video_diffusion_pytorch/space_diffusion.py official repository unverified MIT (permissive) · 9cf6b68718b21b4c · report

Tasks

Future predictionPredictionUnconditional Video GenerationVideo GenerationVideo Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections