mlsanityData to 7 Oct 2026

VideoGigaGAN: Towards Detail-rich Video Super-Resolution

arXiv 2404.12388 ↗First posted 18 Apr 2024cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Video super-resolution (VSR) approaches have shown impressive temporal consistency in upsampled videos. However, these approaches tend to generate blurrier results than their image counterparts as they are limited in their generative capability. This raises a fundamental question: can we extend the success of a generative image upsampler to the VSR task while preserving the temporal consistency? We introduce VideoGigaGAN, a new generative VSR model that can produce videos with high-frequency details and temporal consistency. VideoGigaGAN builds upon a large-scale image upsampler -- GigaGAN. Simply inflating GigaGAN to a video model by adding temporal modules produces severe temporal flickering. We identify several key issues and propose techniques that significantly improve the temporal consistency of upsampled videos. Our experiments show that, unlike previous VSR methods, VideoGigaGAN generates temporally consistent videos with more fine-grained appearance details. We validate the effectiveness of VideoGigaGAN by comparing it with state-of-the-art VSR models on public datasets and showcasing video results with 8× super-resolution.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 62 of its 81 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

62 of 81 references.

References · 62

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  7. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  8. 2022Video Diffusion Modelscited by 2,280
  9. 2017Improved Training of Wasserstein GANscited by 2,223
  10. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  11. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
38 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  2. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  4. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  5. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  6. 2018Which Training Methods for GANs do actually Converge?cited by 672
  7. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  8. 2017Video Enhancement with Task-Oriented Flowcited by 612
  9. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  10. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  11. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  12. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  13. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  14. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  15. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
  16. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  17. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  18. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  19. 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Modelscited by 284
  20. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  21. 2023Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translationcited by 253
  22. 2018Learning Blind Video Temporal Consistencycited by 247
  23. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  24. 2017Stochastic Variational Video Predictioncited by 234
  25. 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 225
  26. 2022VRT: A Video Restoration Transformercited by 219
  27. 2019Scaling Autoregressive Video Modelscited by 189
  28. 2018Stochastic Adversarial Video Predictioncited by 173
  29. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  30. 2018Frame-Recurrent Video Super-Resolutioncited by 160
  31. 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
  32. 2017Detail-revealing Deep Video Super-resolutioncited by 147
  33. 2019Recurrent Back-Projection Network for Video Super-Resolutioncited by 147
  34. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  35. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  36. 2020Video Super-Resolution with Recurrent Structure-Detail Networkcited by 116
  37. 2022Generating Long Videos of Dynamic Scenescited by 113
  38. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 13; 2026: 10.

30 papers.

Sort:

By area:

  1. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  2. 2024LLMs Meet Multimodal Generation and Editing: A Surveycited by 35
  3. 2024SuperGaussian: Repurposing Video Models for 3D Super Resolutioncited by 22
  4. 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolutioncited by 14
  5. 20243DEnhancer: Consistent Multi-View Diffusion for 3D Enhancementcited by 12
  6. 2025Enhance-A-Video: Better Generated Video for Freecited by 11
  7. 2024AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Contentcited by 7
  8. 2025Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusioncited by 7
  9. 2025Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Frameworkcited by 5
  10. 2025OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesiscited by 4
  11. 2026Improved Adversarial Diffusion Compression for Real-World Video Super-Resolutioncited by 4
  12. 2026DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolutioncited by 4
18 more
  1. 2024Sequence Matters: Harnessing Video Models in 3D Super-Resolutioncited by 3
  2. 2025Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generationcited by 3
  3. 2025Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolutioncited by 2
  4. 2024DaBiT: Depth and Blur informed Transformer for Video Focal Deblurringcited by 1
  5. 2024Subjective and Objective Quality Evaluation of Super-Resolution Enhanced Broadcast Images on a Novel SR-IQA Datasetcited by 1
  6. 2025Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospectscited by 1
  7. 2025CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videoscited by 1
  8. 2026Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusioncited by 1
  9. 2026From Blurry to Believable: Enhancing Low-quality Talking Heads with 3D Generative Priorscited by 1
  10. 2025Crafting Query-Aware Selective Attention for Single Image Super-Resolutioncited by 0
  11. 2025MambaVSR: Content-Aware Scanning State Space Model for Video Super-Resolutioncited by 0
  12. 2025STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolutioncited by 0
  13. 2026Compressed-Domain-Aware Online Video Super-Resolutioncited by 0
  14. 2026GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidancecited by 0
  15. 2026AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolutioncited by 0
  16. 2026AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splattingcited by 0
  17. 2026DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolutioncited by 0
  18. 2026ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routingcited by 0