Research map / Video / Video generation
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DIGAN instead of MoCoGAN-HD | video generation · UCF-101 train+test split | FVD: 838 -> 577 | Helped |
| use DIGAN instead of MoCoGAN-HD | video generation · Sky | FVD: 183.6±5.2 -> 114.6±4.3 | Helped |
| use DIGAN instead of MoCoGAN-HD | video generation · TaiChi | FVD: 144.7±6.0 -> 128.1±4.9 | Helped |
| use DIGAN instead of MoCoGAN-HD | video generation · Kinetics-food | FVD: 430.4±29.9 -> 313.3±36.9 | Helped |
| use smaller temporal frequency (ablation) | DIGAN generator · UCF-101 | FVD: 686±25 -> 640±22 | Helped |
| add a motion vector (ablation) | DIGAN generator with smaller temporal frequency · UCF-101 | FVD: 640±22 -> 585±27 | Helped |
| add nonlinear MLP mapping to motion features (ablation) | DIGAN generator with smaller temporal frequency and motion vector · UCF-101 | FVD: 585±27 -> 577±21 | Helped |
| add the content vector to motion generation (ablation) | DIGAN · UCF-101 | FVD: 596±26 -> 577±21 | Helped |
| add the content vector to motion generation (ablation) | DIGAN · TaiChi | FVD: 147.9±4.9 -> 128.1±4.9 | Helped |
| use continuous DIGAN dynamics instead of StyleGAN2 latent interpolation | intermediate-frame prediction · TaiChi | SSIM: 0.5639 -> 0.6753 | Helped |
Closest papers by meaning
- Generative Inbetweening through Frame-wise Conditions-Driven Video Generation (CVPR 2025 · similarity 0.86)
- Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation (NeurIPS 2025 · similarity 0.86)
- Bias for Action: Video Implicit Neural Representations with Bias Modulation (CVPR 2025 · similarity 0.85)
- Generative Pre-trained Autoregressive Diffusion Transformer (NeurIPS 2025 · similarity 0.85)
- SF-V: Single Forward Video Generation Model (NeurIPS 2024 · similarity 0.85)
- OSV: One Step is Enough for High-Quality Image to Video Generation (CVPR 2025 · similarity 0.85)
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.