mlsanityData to 7 Oct 2026

StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2

arXiv 2112.14683 ↗First posted 29 Dec 2021cs.CV cs.AI cs.LGcited by 300

Not on the map. Why?

Cited by 115 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Videos show continuous events, yet most - if not all - video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be - time-continuous signals, and extend the paradigm of neural representations to build a continuous-time video generator. For this, we first design continuous motion representations through the lens of positional embeddings. Then, we explore the question of training on very sparse videos and demonstrate that a good generator can be learned by using as few as 2 frames per clip. After that, we rethink the traditional image + video discriminators pair and design a holistic discriminator that aggregates temporal information by simply concatenating frames' features. This decreases the training cost and provides richer learning signal to the generator, making it possible to train directly on 10242 videos for the first time. We build our model on top of StyleGAN2 and it is just ≈5% more expensive to train at the same resolution while achieving almost the same image quality. Moreover, our latent space features similar properties, enabling spatial manipulations that our method can propagate in time. We can generate arbitrarily long videos at arbitrary high frame rate, while prior work struggles to generate even 64 frames at a fixed rate. Our model is tested on four modern 2562 and one 10242-resolution video synthesis benchmarks. In terms of sheer metrics, it performs on average ≈30% better than the closest runner-up. Project website: https://universome.github.io.

Key facts. Cited by 300 papers in the map (data through 7 Oct 2026). Builds on 68 of its 84 references that are in the map. First posted on arXiv 29 Dec 2021.

Builds on

68 of 84 references.

References · 68

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  11. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
38 more
  1. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  2. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  5. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  6. 2020Convolutional Occupancy Networkscited by 760
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  8. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  9. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  10. 2020First Order Motion Model for Image Animationcited by 698
  11. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  12. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  13. 2018Which Training Methods for GANs do actually Converge?cited by 672
  14. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  15. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  16. 2015Unsupervised Learning of Video Representations using LSTMscited by 434
  17. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  18. 2018Video-to-Video Synthesiscited by 388
  19. 2016Generating Videos with Scene Dynamicscited by 376
  20. 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
  21. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  22. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  23. 2021NeRV: Neural Representations for Videoscited by 255
  24. 2018cGANs with Projection Discriminatorcited by 253
  25. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  26. 2019Depth-Aware Video Frame Interpolationcited by 232
  27. 2017Video Frame Interpolation via Adaptive Separable Convolutioncited by 211
  28. 2016Temporal Generative Adversarial Nets with Singular Value Clippingcited by 198
  29. 2019Scaling Autoregressive Video Modelscited by 189
  30. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  31. 2017Optimizing the Latent Space of Generative Networkscited by 157
  32. 2020Adversarial Generation of Continuous Imagescited by 135
  33. 2018Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GANcited by 120
  34. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 118
  35. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 111
  36. 2016Video Pixel Networkscited by 108
  37. 2020Latent Video Transformercited by 106
  38. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 105

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 38; 2023: 83; 2024: 86; 2025: 69; 2026: 24.

300 papers.

Sort:

By area:

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  2. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  3. 2023ModelScope Text-to-Video Technical Reportcited by 651
  4. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 618
  5. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  6. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
  7. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 568
  8. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
  9. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  10. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  11. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 343
  12. 2022MAGVIT: Masked Generative Video Transformercited by 341
38 more
  1. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 332
  2. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 330
  3. 2023Pix2Video: Video Editing using Image Diffusioncited by 318
  4. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 309
  5. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generationcited by 300
  6. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 285
  7. 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Modelscited by 284
  8. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
  9. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  10. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Predictioncited by 231
  11. 2024VideoPhy: Evaluating Physical Commonsense for Video Generationcited by 215
  12. 2023A Survey on Video Diffusion Modelscited by 203
  13. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  14. 2023DreamVideo: Composing Your Dream Videos with Customized Subject and Motioncited by 186
  15. 2024VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Timecited by 186
  16. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  17. 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 180
  18. 2023FreeNoise: Tuning-Free Longer Video Diffusion via Noise Reschedulingcited by 173
  19. 2023MotionDirector: Motion Customization of Text-to-Video Diffusion Modelscited by 172
  20. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  21. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  22. 2023Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generationcited by 153
  23. 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 144
  24. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  25. 2024FIFO-Diffusion: Generating Infinite Videos from Text without Trainingcited by 134
  26. 2024ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generationcited by 130
  27. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  28. 2024OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generationcited by 117
  29. 2022Generating Long Videos of Dynamic Scenescited by 113
  30. 2025Long Context Tuning for Video Generationcited by 110
  31. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  32. 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesiscited by 105
  33. 2023CelebV-Text: A Large-Scale Facial Text-Video Datasetcited by 103
  34. 2023SimDA: Simple Diffusion Adapter for Efficient Video Generationcited by 101
  35. 2025One-Minute Video Generation with Test-Time Trainingcited by 100
  36. 2023Human Motion Generation: A Surveycited by 95
  37. 2023Generative Image Dynamicscited by 93
  38. 2023FreeInit: Bridging Initialization Gap in Video Diffusion Modelscited by 93

50 most cited of 300 All 300 (JSON)