{"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/hierarchical-patch-diffusion-models-for-high-1","title":"Hierarchical Patch Diffusion Models for High-Resolution Video Generation","arxiv_id":"2406.07792","date":"2024-06-12","proceeding":"CVPR 2024 1","authors":["Ivan Skorokhodov","Willi Menapace","Aliaksandr Siarohin","Sergey Tulyakov"],"abstract":"Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring the diffusion pipeline into multiple independent components, limiting scalability and complicating downstream applications. This makes it very efficient during training and unlocks end-to-end optimization on high-resolution videos. We improve PDMs in two principled ways. First, to enforce consistency between patches, we develop deep context fusion -- an architectural technique that propagates the context information from low-scale to high-scale patches in a hierarchical manner. Second, to accelerate training and inference, we propose adaptive computation, which allocates more network capacity and computation towards coarse image details. The resulting model sets a new state-of-the-art FVD score of 66.32 and Inception Score of 87.68 in class-conditional video generation on UCF-101 $256^2$, surpassing recent methods by more than 100%. Then, we show that it can be rapidly fine-tuned from a base $36\\times 64$ low-resolution generator for high-resolution $64 \\times 288 \\times 512$ text-to-video synthesis. To the best of our knowledge, our model is the first diffusion-based architecture which is trained on such high resolutions entirely end-to-end. Project webpage: https://snap-research.github.io/hpdm.","url_abs":"https://arxiv.org/abs/2406.07792v1","url_pdf":"https://arxiv.org/pdf/2406.07792v1.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":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset":"UCF-101","model":"HPDM-L","rank_in_archive_order":6,"of":48,"metrics":{"FVD16":"66.32","Inception Score":"87.68"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.07792","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}