Research map / Video / Video segmentation and tracking
StyleGAN-V: A Continuous Video Generator With the Price, Image Quality and Perks of StyleGAN2
Ivan Skorokhodov, Sergey Tulyakov, Mohamed Elhoseiny
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use StyleGAN-V rather than MoCoGAN+SG2 | FaceForensics 256² video generation · FaceForensics 256² | FVD16: 55.62 -> 47.41 | Improved |
| Use StyleGAN-V rather than DIGAN | SkyTimelapse 256² video generation · SkyTimelapse 256² | FVD16: 83.11 -> 79.52 | Improved |
| Use StyleGAN-V rather than DIGAN | SkyTimelapse 256² video generation · SkyTimelapse 256² | FVD128: 196.7 -> 197.0 | Hurt |
| Use StyleGAN-V rather than DIGAN | UCF101 256² video generation · UCF101 256² | FVD16: 1630.2 -> 1431.0 | Improved |
| Use StyleGAN-V rather than VideoGPT | RainbowJelly 256² video generation · RainbowJelly 256² | FVD16: 136.0 -> 195.4 | Hurt |
| Use StyleGAN-V rather than DIGAN | RainbowJelly 256² video generation · RainbowJelly 256² | FVD128: 369.0 -> 262.5 | Improved |
| Add the StyleGAN-V generator rather than use the MoCoGAN+SG2 generator (ablation) | StyleGAN-V · FaceForensics 256² | FVD16: 65.88 -> 47.41 | Improved |
| Add the StyleGAN-V generator rather than use the MoCoGAN+SG2 generator (ablation) | StyleGAN-V · SkyTimelapse 256² | FVD16: 109.1 -> 79.52 | Improved |
| Add the StyleGAN-V discriminator rather than use the MoCoGAN+SG2 discriminator (ablation) | StyleGAN-V · FaceForensics 256² | FVD16: 154.0 -> 47.41 | Improved |
| Add the StyleGAN-V discriminator rather than use the MoCoGAN+SG2 discriminator (ablation) | StyleGAN-V · SkyTimelapse 256² | FVD16: 236.9 -> 79.52 | Improved |
| Add discriminator conditioning on time distances (ablation) | StyleGAN-V · FaceForensics 256² | FVD16: 95.4 -> 47.41 | Improved |
| Add discriminator conditioning on time distances (ablation) | StyleGAN-V · SkyTimelapse 256² | FVD16: 102.1 -> 79.52 | Improved |
Later papers that compared with this method
13 later accepted papers report StyleGAN-V as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.
- Controllable Video Generation with Provable Disentanglement (ICLR 2026 · better on 5 of 5 shared results)
- STDD: Spatio-Temporal Dual Diffusion for Video Generation (CVPR 2025 · better on 2 of 2 shared results)
- Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction (CVPR 2025 · better on 1 of 1 shared result)
- LEO: Generative Latent Image Animator for Human Video Synthesis (IJCV 2024 · better on 3 of 4 shared results)
- FIFO-Diffusion: Generating Infinite Videos from Text without Training (NeurIPS 2024 · better on 1 of 1 shared result)
- Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation (ECCV 2024 · better on 1 of 1 shared result)
- Towards Smooth Video Composition (ICLR 2023 · better on 10 of 11 shared results)
- MoStGAN-V: Video Generation With Temporal Motion Styles (CVPR 2023 · better on 8 of 8 shared results)
5 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation (ICCV 2023 · similarity 0.91)
- MoStGAN-V: Video Generation With Temporal Motion Styles (CVPR 2023 · similarity 0.89)
- VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis (ICLR 2025 · similarity 0.88)
- OSV: One Step is Enough for High-Quality Image to Video Generation (CVPR 2025 · similarity 0.87)
- Optical-Flow Guided Prompt Optimization for Coherent Video Generation (CVPR 2025 · similarity 0.87)
- TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
