Research map / 3D vision / Face and shape
Combining Generative and Geometry Priors for Wide-Angle Portrait Correction
Lan Yao, Chaofeng Chen, Xiaoming Li, Zifei Yan, Wangmeng Zuo
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 |
|---|---|---|---|
| add symmetry loss to LineCNet (ablation) | wide-angle portrait correction · Wide-angle portrait dataset | LineAcc: 66.192 -> 67.304 | Improved |
| add StyleGAN generative face prior to FaceCNet (ablation) | wide-angle portrait correction · Wide-angle portrait dataset | ShapeAcc: 97.027 -> 99.012 | Improved |
| add StyleGAN generative face prior to FaceCNet (ablation) | wide-angle portrait correction · Wide-angle portrait dataset | Landmark Distance: 5.991 -> 5.3397 | Improved |
| add generative prior on top of symmetry prior (ablation) | wide-angle portrait correction · Wide-angle portrait dataset | Landmark Distance: 5.5464 -> 5.013 | Improved |
| add generative prior (ablation) | wide-angle portrait correction · Wide-angle portrait dataset | LineAcc: 66.192 -> 66.192 | No clear effect |
| use multi-scale StyleGAN features instead of single smallest scale (ablation) | FaceCNet · Face correction | Landmark Distance: 2.908 -> 2.357 | Improved |
| add single-scale StyleGAN feature (ablation) | FaceCNet · Face correction | PSNR: 25.586 -> 24.335 | Hurt |
| add multi-scale StyleGAN features (ablation) | FaceCNet · Face correction | PSNR: 25.586 -> 26.732 | Improved |
Closest papers by meaning
- Practical Wide-Angle Portraits Correction With Deep Structured Models (CVPR 2021 · similarity 0.90)
- DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs (IJCV 2024 · similarity 0.88)
- Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis (ICCV 2023 · similarity 0.87)
- Learning Perspective Undistortion of Portraits (ICCV 2019 · similarity 0.87)
- Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis From Monocular Image (CVPR 2023 · similarity 0.86)
- MaDCoW: Marginal Distortion Correction for Wide-Angle Photography with Arbitrary Objects (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.
