{"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/preserve-your-own-correlation-a-noise-prior","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","arxiv_id":"2305.10474","date":"2023-05-17","proceeding":"ICCV 2023 1","authors":["Songwei Ge","Seungjun Nah","Guilin Liu","Tyler Poon","Andrew Tao","Bryan Catanzaro","David Jacobs","Jia-Bin Huang","Ming-Yu Liu","Yogesh Balaji"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2305.10474v3","url_pdf":"https://arxiv.org/pdf/2305.10474v3.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":[],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-video-generation-on-ucf-101","task":"Text-to-Video Generation","dataset":"UCF-101","model":"PYoCo (Zero-shot, 64x64)","rank_in_archive_order":7,"of":10,"metrics":{"FVD16":"355.19"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset":"UCF-101","model":"PYoCo (Zero-shot, 64x64, unconditional)","rank_in_archive_order":23,"of":48,"metrics":{"FVD16":"310","Inception Score":"60.01"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset":"UCF-101","model":"PYoCo (Zero-shot, 64x64, text-conditional)","rank_in_archive_order":30,"of":48,"metrics":{"FVD16":"355.19","Inception Score":"47.76"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.10474","atlas_url":"https://app.syntology.ai/?focus=2305.10474","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}