Research map / Video / Video generation
Controllable Video Generation with Provable Disentanglement
Yifan Shen, Peiyuan Zhu, Zijian Li, Shaoan Xie, Namrata Deka, Zongfang Liu, Zeyu Tang, Guangyi Chen, Kun Zhang
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 GRU with vanilla RNN in the temporal transition module (ablation) | CoVoGAN · FaceForensics | MCC (%): 33.78 -> 26.59 | Hurt |
| replace GRU with vanilla RNN (ablation) | CoVoGAN · FaceForensics | FVD16: 48.80 -> 53.68 | Hurt |
| replace component-wise flow with fully connected MLP (ablation) | CoVoGAN · FaceForensics | MCC (%): 33.78 -> 8.22 | Hurt |
| replace component-wise flow with MLP (ablation) | CoVoGAN · FaceForensics | FVD16: 48.80 -> 82.81 | Hurt |
| add temporal transition module (disentangled latents) to GAN versus MoStGAN-V | StyleGAN2-ADA video GAN · FaceForensics | MCC (%): 27.95 -> 33.78 | Improved |
| use CoVoGAN vs Latte on SkyTimelapse | CoVoGAN · SkyTimelapse | FVD16: 46.51 vs 41.84 (FVD16); 35.58 vs 40.21 (FVD8) | Mixed |
| use CoVoGAN for longer 32-frame videos vs MoStGAN-V | CoVoGAN · FaceForensics 32 frames | MCC (%): 14.23 -> 29.99 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MoStGAN-V — MoStGAN-V: Video Generation With Temporal Motion Styles (CVPR 2023) · better on 8 of 8 shared results
- StyleGAN-V — StyleGAN-V: A Continuous Video Generator With the Price, Image Quality and Perks of StyleGAN2 (CVPR 2022) · better on 5 of 5 shared results
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
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.88)
- Frame In-N-Out: Unbounded Controllable Image-to-Video Generation (NeurIPS 2025 · similarity 0.87)
- DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation (CVPR 2025 · similarity 0.87)
- OSV: One Step is Enough for High-Quality Image to Video Generation (CVPR 2025 · similarity 0.86)
- IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner (CVPR 2025 · similarity 0.86)
- Generative Inbetweening through Frame-wise Conditions-Driven Video Generation (CVPR 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.
