Research map / Video / Video generation
Controllable Image-to-Video Translation: A Case Study on Facial Expression Generation
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 the proposed controllable generator instead of ConvLSTM | Facial expression video generation · Web test faces, mean across Happy, Surprise, and Angry | AMT preference: 83.0% | Helped |
| Use the proposed controllable generator instead of HP | Facial expression video generation · Web test faces, mean across Happy, Surprise, and Angry | AMT preference: 71.4% | Helped |
| Use the proposed method rather than either baseline | Facial expression video generation · Web test faces, mean across expressions | AMT preference: 65.1% | Helped |
| Add a local discriminator for the mouth region (ablation) | Proposed facial expression generator · Facial expression videos | Visual quality | Helped |
| Add landmark prediction (ablation) | Proposed facial expression generator · Facial expression videos | Visual clarity | Helped |
| Add temporal continuity regularization (ablation) | Proposed facial expression generator · Facial expression videos | Temporal continuity | Helped |
| Train one joint model for multiple expressions instead of separate models | Facial expression generator · Happy and Angry expression generation | Visual realism | Helped |
Closest papers by meaning
- Neural Emotion Director: Speech-Preserving Semantic Control of Facial Expressions in "In-the-Wild" Videos (CVPR 2022 · similarity 0.89)
- FG-EmoTalk: Talking Head Video Generation with Fine-Grained Controllable Facial Expressions (AAAI 2024 · similarity 0.86)
- VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis (CVPR 2025 · similarity 0.85)
- RealPortrait: Realistic Portrait Animation with Diffusion Transformers (AAAI 2025 · similarity 0.85)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 2024 · similarity 0.85)
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (ICLR 2024 · 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.