Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
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 $10\times$ smaller model using significantly less computation than the prior art.
PDF Abstract ICCV 2023 PDF ICCV 2023 AbstractTask | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Video Generation | UCF-101 | PYoCo (Zero-shot, 64x64, unconditional) | Inception Score | 60.01 | # 9 | |
FVD16 | 310 | # 13 | ||||
Video Generation | UCF-101 | PYoCo (Zero-shot, 64x64, text-conditional) | Inception Score | 47.76 | # 15 | |
FVD16 | 355.19 | # 19 | ||||
Text-to-Video Generation | UCF-101 | PYoCo (Zero-shot, 64x64) | FVD16 | 355.19 | # 8 |