UltraGen: High-Resolution Video Generation with Hierarchical Attention
Teng Hu, Jiangning Zhang, Zihan Su, Ran Yi
2026年份
7被引次数
7顶会引用
摘要
UltraGen Figure 1 . Typical video generation models exhibit significant quality degradation and increased processing time with higher resolutions, whereas our UltraGen delivers superior video quality at resolutions beyond 2K while achieving 4.78× speedup compared to the popular Wan-T2V-1.3B baseline [32] (81 frames, 4×H20 GPUs). Enlarge for better visual effects.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper7
- Harmony: Harmonizing Audio and Video Generation through Cross-Task SynergyTeng Hu, Zhentao Yu, Guozhen Zhang, Zihan Su 等CVPR 2026 · 被引用 21 次
- PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and EnhancementTeng Hu, Zhentao Yu, Zhengguang Zhou, Jiangning Zhang 等NeurIPS 2025 · 被引用 15 次
- Multi-view Pyramid Transformer: Look Coarser to See BroaderGyeongjin Kang, Seungkwon Yang, Seungtae Nam, Younggeun Lee 等CVPR 2026 · 被引用 8 次
- Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal AnimationJiangning Zhang, junwei zhu, Zhenye Gan, Donghao Luo 等CVPR 2026 · 被引用 4 次
- Transform Trained Transformer for Accelerating Native 4K Video GenerationJiangning Zhang, Junwei Zhu, Teng Hu, Yabiao Wang 等ICML 2026 · 被引用 3 次
它引用的顶会 Paper23
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu 等ICCV 2021 · 被引用 31,683 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
相关 Paper
- SURF: Signature-Retained Fast Video GenerationKaixin Ding, Xi Chen, Sihui Ji, Yuan Gao 等CVPR 2026 · 被引用 2 次
- MAGVIT: Masked Generative Video TransformerLijun Yu, Yong Cheng, Kihyuk Sohn, José Lezama 等CVPR 2023
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video SynthesisFeng Liang, Bichen Wu, Jialiang Wang, Licheng Yu 等CVPR 2024
- Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video SynthesisJingjing Ren, Wenbo Li, Zhongdao Wang, Haoze Sun 等ICCV 2025 · 被引用 3 次
- SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video RestorationJianyi Wang, Zhijie Lin, Meng Wei, Yang Zhao 等CVPR 2025
