Research map / Image generation / Super-resolution
Face Super-Resolution Guided by 3D Facial Priors
Xiaobin Hu, Wenqi Ren, John LaMaster, Xiaochun Cao, Xiaoming Li, Zechao Li, Bjoern Menze, Wei Liu
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 3D facial priors to VDSR (ablation) | VDSR · CelebA test (x8) | PSNR: 22.76 -> 24.66 | Improved |
| add 3D facial priors to VDSR (ablation) | VDSR · CelebA test (x4) | PSNR: 28.13 -> 29.29 | Improved |
| add 3D facial priors to VDSR (ablation) | VDSR · Menpo left pose (x4) | PSNR: 26.99 -> 28.62 | Improved |
| add 3D facial priors to VDSR (ablation) | VDSR · Menpo right pose (x4) | PSNR: 26.85 -> 28.89 | Improved |
| add 3D facial priors to VDSR (ablation) | VDSR · Menpo semi-frontal pose (x4) | PSNR: 25.63 -> 26.99 | Improved |
| add Spatial Attention Module on top of 3D priors (ablation) | VDSR+3D · CelebA test (x8) | PSNR: 24.66 -> 25.39 | Improved |
| add Spatial Attention Module on top of 3D priors (ablation) | VDSR+3D · CelebA test (x4) | PSNR: 29.29 -> 29.69 | Improved |
| add Spatial Attention Module on top of 3D priors (ablation) | VDSR+3D · CelebA test (x8) | SSIM: 0.7127 -> 0.7551 | Improved |
| use 3D priors instead of 2D landmark/parsing priors | SAM3D vs PSR-FAN and FSRNet · CelebA test (x8) | PSNR: 22.66 -> 25.39 | Improved |
| use 3D priors instead of 2D landmark/parsing priors | SAM3D vs FSRNet · Menpo left pose (x8) | PSNR: 23.56 -> 23.80 | Improved |
| add rendered 3D priors and SAM to baseline (ablation) | SAM3D · qualitative ablation (x8) | visual quality | 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.
- FSRNet — FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018) · better on 2 of 2 shared results
- Wavelet-SRNet — Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution (ICCV 2017) · better on 2 of 2 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
- Face Restoration via Plug-and-Play 3D Facial Priors (TPAMI 2021 · similarity 0.93)
- Face Super-resolution Guided by Facial Component Heatmaps (ECCV 2018 · similarity 0.92)
- PortraitSR: Artist-Inspired Prior Learning for Progressive Face Super-Resolution (AAAI 2026 · similarity 0.91)
- FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018 · similarity 0.90)
- Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation (CVPR 2020 · similarity 0.89)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (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.
