mlsanityData to 7 Oct 2026

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

arXiv 2501.01320 ↗First posted 2 Jan 2025cs.CVcited by 62

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Video restoration poses non-trivial challenges in maintaining fidelity while recovering temporally consistent details from unknown degradations in the wild. Despite recent advances in diffusion-based restoration, these methods often face limitations in generation capability and sampling efficiency. In this work, we present SeedVR, a diffusion transformer designed to handle real-world video restoration with arbitrary length and resolution. The core design of SeedVR lies in the shifted window attention that facilitates effective restoration on long video sequences. SeedVR further supports variable-sized windows near the boundary of both spatial and temporal dimensions, overcoming the resolution constraints of traditional window attention. Equipped with contemporary practices, including causal video autoencoder, mixed image and video training, and progressive training, SeedVR achieves highly-competitive performance on both synthetic and real-world benchmarks, as well as AI-generated videos. Extensive experiments demonstrate SeedVR's superiority over existing methods for generic video restoration.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 71 of its 81 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

71 of 81 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models1 Jul
  2. 2024Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer7 May
  3. 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution25 Mar
  4. 2024Efficient Diffusion Model for Image Restoration by Residual Shifting12 Mar
  5. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution11 Dec
  6. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution1 Dec
  7. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution27 Nov
  8. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting23 Jul
  9. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  10. 2022DifFace: Blind Face Restoration with Diffused Error Contraction13 Dec

Other references · 61

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2022Generative Adversarial Networkscited by 5,603
  12. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
38 more
  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  3. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  6. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  7. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  8. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  9. 2021Video Swin Transformercited by 1,090
  10. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  11. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  12. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  13. 2020Pre-Trained Image Processing Transformercited by 891
  14. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  15. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  16. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 637
  17. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  18. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  19. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  20. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  21. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  22. 2023VideoComposer: Compositional Video Synthesis with Motion Controllabilitycited by 461
  23. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  24. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  25. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
  26. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
  27. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  28. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 294
  29. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  30. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
  31. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
  32. 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 225
  33. 2022VRT: A Video Restoration Transformercited by 219
  34. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  35. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  36. 2024Tora: Trajectory-oriented Diffusion Transformer for Video Generationcited by 161
  37. 2018Frame-Recurrent Video Super-Resolutioncited by 160
  38. 2017Detail-revealing Deep Video Super-resolutioncited by 147

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 31; 2026: 31.

62 papers.

Sort:

By area:

  1. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 126
  2. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 81
  3. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  4. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  5. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  6. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  7. 2025BindWeave: Subject-Consistent Video Generation via Cross-Modal Integrationcited by 22
  8. 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolutioncited by 14
  9. 2025Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesiscited by 13
  10. 2025DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradationscited by 11
  11. 2025Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restorationcited by 10
  12. 2026MV-S2V: Multi-View Subject-Consistent Video Generationcited by 9
38 more
  1. 2025InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolutioncited by 8
  2. 2025HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streamingcited by 8
  3. 2025SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tilingcited by 6
  4. 2025SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolutioncited by 5
  5. 2025DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolutioncited by 5
  6. 2026SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagationcited by 5
  7. 2025LiftVSR: Lifting Image Diffusion to Video Super-Resolution via Hybrid Temporal Modeling with Only 4×RTX 4090scited by 4
  8. 2025RealisVSR: Detail-enhanced Diffusion for Real-World 4K Video Super-Resolutioncited by 4
  9. 2026Improved Adversarial Diffusion Compression for Real-World Video Super-Resolutioncited by 4
  10. 2026DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolutioncited by 4
  11. 2025OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolutioncited by 3
  12. 2025Asymmetric VAE for One-Step Video Super-Resolution Accelerationcited by 3
  13. 2025Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generationcited by 3
  14. 2025Learning Zero-Shot Subject-Driven Video Generation Using 1% Computecited by 2
  15. 2025Causal-Entity Reflected Egocentric Traffic Accident Video Synthesiscited by 2
  16. 2025QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolutioncited by 2
  17. 2025Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolutioncited by 2
  18. 2025UniTS: Unified Spatio-Temporal Generative Model for Remote Sensingcited by 2
  19. 2026FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Modelscited by 2
  20. 2026SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Controlcited by 2
  21. 2026SwiftVR: Real-Time One-Step Generative Video Restorationcited by 2
  22. 2025UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolutioncited by 1
  23. 2025SkipSR: Faster Super Resolution with Token Skippingcited by 1
  24. 2025UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Frameworkcited by 1
  25. 2025CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videoscited by 1
  26. 2026Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusioncited by 1
  27. 2026LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolutioncited by 1
  28. 2026PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolutioncited by 1
  29. 2026SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blendingcited by 1
  30. 2026TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolutioncited by 1
  31. 2025STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolutioncited by 0
  32. 2026Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Modelscited by 0
  33. 2026Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolutioncited by 0
  34. 2026VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thoughtcited by 0
  35. 2026Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rayscited by 0
  36. 2026DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restorationcited by 0
  37. 2026DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolutioncited by 0
  38. 2026How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?cited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025DiTVR: Zero-Shot Diffusion Transformer for Video Restoration
  2. 2025TDM: Temporally-Consistent Diffusion Model for All-in-One Real-World Video Restoration
  3. 2026D2-VR: Degradation-Robust and Distilled Video Restoration with Synergistic Optimization Strategy
  4. 2024AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
  5. 2024Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compression
  6. 2025Temporal-Consistent Video Restoration with Pre-trained Diffusion Models
  7. 2025UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
  8. 2026DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer