Papers › Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

17 May 2023ICCV 2023 1arXiv:2305.10474archive 2025-07-28

Songwei Ge, Seungjun Nah, Guilin Liu, Tyler Poon, Andrew Tao, Bryan Catanzaro, David Jacobs, Jia-Bin Huang, Ming-Yu Liu, Yogesh Balaji

Despite tremendous progress in generating high-quality images using diffusion models, synthesizing a sequence of animated frames that are both photorealistic and temporally coherent is still in its infancy. While off-the-shelf billion-scale datasets for image generation are available, collecting similar video data of the same scale is still challenging. Also, training a video diffusion model is computationally much more expensive than its image counterpart. In this work, we explore finetuning a pretrained image diffusion model with video data as a practical solution for the video synthesis task. We find that naively extending the image noise prior to video noise prior in video diffusion leads to sub-optimal performance. Our carefully designed video noise prior leads to substantially better performance. Extensive experimental validation shows that our model, Preserve Your Own Correlation (PYoCo), attains SOTA zero-shot text-to-video results on the UCF-101 and MSR-VTT benchmarks. It also achieves SOTA video generation quality on the small-scale UCF-101 benchmark with a 10× smaller model using significantly less computation than the prior art.

PaperPDFConference PDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationText-to-Video GenerationVideo Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Video Generation UCF-101 PYoCo (Zero-shot, 64x64) FVD16 355.19 #7 of 10 Archive leaderboard report
Video Generation UCF-101 PYoCo (Zero-shot, 64x64, unconditional) FVD16 310 #23 of 48 Archive leaderboard report
Video Generation UCF-101 PYoCo (Zero-shot, 64x64, unconditional) Inception Score 60.01 #23 of 48 Archive leaderboard report
Video Generation UCF-101 PYoCo (Zero-shot, 64x64, text-conditional) FVD16 355.19 #30 of 48 Archive leaderboard report
Video Generation UCF-101 PYoCo (Zero-shot, 64x64, text-conditional) Inception Score 47.76 #30 of 48 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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