Research map / 3D vision / Face and shape
Photo-Realistic Facial Details Synthesis From Single Image
Anpei Chen, Zhang Chen, Guli Zhang, Kenny Mitchell, Jingyi Yu
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 emotion-informed expression prediction instead of landmark-only expression fitting (3DDFA, ExpNet) for the proxy face | proxy face generation · qualitative proxy comparison | similarity of cheeks, nasolabial folds, eye bags | Improved |
| combine illumination model with face statistics and wrinkle PCA templates (DFDN) instead of illumination-only detail synthesis (Pix2vertex, FPD, Extreme3D) | facial detail synthesis · qualitative close-up meshes | wrinkle realism | Improved |
| use DFDN instead of competing methods for proxy plus displacement geometry | proxy + displacement · strong expressions, error maps | geometry error | Improved |
| add displacement detail on top of the proxy, compared with proxy-only geometry of other methods | proxy mesh · error maps | geometry error | Mixed |
| train PDIM-only loss for first 10 epochs before back-propagating all losses (ablation) | DFDN training · training convergence | loss decrease speed | Improved |
Closest papers by meaning
- Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks (ECCV 2020 · similarity 0.90)
- Learning to Generate Customized Dynamic 3D Facial Expressions (ECCV 2020 · similarity 0.90)
- 3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation (IJCV 2020 · similarity 0.89)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.89)
- AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars (NeurIPS 2022 · similarity 0.88)
- Controllable 3D Face Generation with Conditional Style Code Diffusion (AAAI 2024 · similarity 0.87)
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.
