SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
Jianyi Wang, Zhijie Lin, Meng Wei, Yang Zhao, Ceyuan Yang, Chen Change Loy, Lu Jiang
2025Year
15Top-tier citations
Abstract
Figure 1. Speed and performance comparisons. SeedVR demonstrates impressive restoration capabilities, offering fine details and enhanced visual realism. Despite its 2.48B parameters, SeedVR is over 2× faster than existing diffusion-based video restoration approaches [20, 64, 82]. With delicate designs, SeedVR is as efficient as the Stable Diffusion Upscaler [2], even with five times the parameter count.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d7461b22-34c8-45d9-beba-cafeb624f91cCited by top-tier papers15
- Phantom: Subject-Consistent Video Generation via Cross-Modal AlignmentLijie Liu, Tianxiang Ma, Bingchuan Li, Zhuowei Chen et al.ICCV 2025 · 128 citations
- SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-TrainingJianyi Wang, Shanchuan Lin, Zhijie Lin, Yuxi Ren et al.ICLR 2026 · 51 citations
- FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super ResolutionJunhao Zhuang, Shi Guo, Xin Cai, Xiaohui Li et al.CVPR 2026 · 42 citations
- DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-ResolutionZheng Chen, Zichen Zou, Kewei Zhang, Xiongfei Su et al.NeurIPS 2025 · 31 citations
- Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video RestorationHaoran Bai, Xiaoxu Chen, Canqian Yang, Zongyao He et al.ICLR 2026 · 10 citations
Builds on40
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
Related papers
- Hierarchical Flow Diffusion for Efficient Frame InterpolationYang Hai, Guo Wang, Tan Su, Wenjie Jiang et al.CVPR 2025
- UltraGen: High-Resolution Video Generation with Hierarchical AttentionTeng Hu, Jiangning Zhang, Zihan Su, Ran YiAAAI 2026 · 7 citations
- EVRNet: Efficient Video Restoration on Edge DevicesSachin Mehta, Amit Kumar, Fitsum A. Reda, Varun Nasery et al.ACM MM 2021 · 12 citations
- InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion PriorWeimin Bai, Suzhe Xu, Yiwei Ren, Jinhua Hao et al.CVPR 2026 · 3 citations
- TurboVSR: Fantastic Video Upscalers and Where to Find ThemZhongdao Wang, Guodongfang Zhao, Jingjing Ren, Bailan Feng et al.ICCV 2025
