Research map / Image generation / GANs
Temporal Generative Adversarial Nets With Singular Value Clipping
Masaki Saito, Eiichi Matsumoto, Shunta Saito
Read the paperCheck 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 |
|---|---|---|---|
| replace conventional weight clipping with singular value clipping (ablation) | TGAN · UCF-101 | inception score: 11.77 -> 11.85 | Improved |
| train TGAN with WGAN plus SVC instead of normal GAN (ablation) | TGAN · UCF-101 | inception score: 9.18 -> 11.85 | Improved |
| use SVC instead of weight clipping (ablation) | 3D model · UCF-101 | inception score: 4.32 -> 4.78 | Improved |
| use SVC for training (ablation) | Video GAN · UCF-101 | inception score: 8.18 -> 8.31 | Improved |
| add category conditioning to TGAN | TGAN (SVC) · UCF-101 | inception score: 11.85 -> 15.83 | Improved |
| add temporal generator with per-frame latent variables (z1^t) to G1 (ablation) | TGAN · Moving MNIST | GAM score: 1.03 | Improved |
| use TGAN two-generator design instead of single 3D generator | 3D model (SVC) · Moving MNIST | GAM score: 1.27 | Improved |
Closest papers by meaning
- Train Sparsely, Generate Densely: Memory-Efficient Unsupervised Training of High-Resolution Temporal GAN (IJCV 2020 · similarity 0.90)
- Towards Smooth Video Composition (ICLR 2023 · similarity 0.90)
- Diverse Generation from a Single Video Made Possible (ECCV 2022 · similarity 0.88)
- StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation (ICCV 2023 · similarity 0.88)
- Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks (CVPR 2018 · similarity 0.88)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.86)
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.
