Research map / 3D vision / Face and shape
Realistic Dynamic Facial Textures From a Single Image Using GANs
Kyle Olszewski, Zimo Li, Chao Yang, Yi Zhou, Ronald Yu, Zeng Huang, Sitao Xiang, Shunsuke Saito, Pushmeet Kohli, Hao Li
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 |
|---|---|---|---|
| use conditional GAN texture inference instead of direct delta transfer | Dynamic texture synthesis · Retargeting test sequences | mean L1 loss: 1790 -> 1360 | Improved |
| use conditional GAN texture inference instead of direct delta transfer | Dynamic texture synthesis · Retargeting test sequences | mean L2 loss: 211 -> 152 | Improved |
| use conditional GAN texture inference instead of direct delta transfer | Dynamic texture synthesis · Retargeting test sequences | SSIM: 0.8150 dB -> 0.8730 dB | Improved |
| add skip connections between encoder and decoder layers around the code layer (ablation) | Generator (pix2pix-style) · Texture synthesis | output noise | Improved |
| add SIFT-Flow refinement of the inferred mouth from the source mouth (ablation) | Mouth interior synthesis · Qualitative mouth region | resolution of mouth interior | Improved |
Closest papers by meaning
- Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture (ECCV 2020 · similarity 0.89)
- Realistic Speech-Driven Facial Animation with GANs (IJCV 2019 · similarity 0.88)
- FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning (ICCV 2021 · similarity 0.88)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.87)
- Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer (CVPR 2025 · similarity 0.87)
- Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture (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.
