Research map / Image generation / Super-resolution
Face Super-resolution Guided by Facial Component Heatmaps
Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, Richard Hartley
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 skip connection (ablation) | multi-task upsampling network · Face SR test set (16x16 LR, 8x) | PSNR (dB): 22.69 -> 23.14 | Improved |
| add autoencoder branch instead of upsampling LR directly (ablation) | multi-task upsampling network · Face SR test set (16x16 LR, 8x) | PSNR (dB): 22.83 -> 23.14 | Improved |
| estimate heatmaps on larger feature maps (16 -> 64) (ablation) | HEB · Face SR test set (HEB position ablation) | PSNR (dB): 21.97 -> 23.14 | Improved |
| estimate heatmaps on 32 instead of 16 feature size (ablation) | HEB · Face SR test set (HEB position ablation) | PSNR (dB): 21.97 -> 21.98 | No clear effect |
| increase hourglass stacks from 1 to 4 (ablation) | HEB · Face SR test set (HEB depth ablation) | PSNR (dB): 22.32 -> 23.14 | Improved |
| increase hourglass stacks from 3 to 4 (ablation) | HEB · Face SR test set (HEB depth ablation) | PSNR (dB): 22.93 -> 23.14 | Improved |
| add heatmap (face structure) loss Lh to pixel loss (ablation) | MTUN · Face SR test set (loss ablation) | PSNR (dB): 21.43 -> 23.23 | Improved |
| add feature-wise loss to pixel + heatmap loss (ablation) | MTUN · Face SR test set (loss ablation) | PSNR (dB): 23.23 -> 23.35 | Improved |
| add discriminative loss to pixel + feature + heatmap loss (ablation) | MTUN · Face SR test set (loss ablation) | PSNR (dB): 23.35 -> 23.14 | Mixed |
| retrain TDAE on the paper's training data | TDAE · Face SR test set (16x16 LR, 8x) | PSNR (dB): 18.87 -> 21.39 | Improved |
Closest papers by meaning
- FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors (CVPR 2018 · similarity 0.93)
- Face Super-Resolution Guided by 3D Facial Priors (ECCV 2020 · similarity 0.92)
- Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes (CVPR 2018 · similarity 0.91)
- Semantic Face Hallucination: Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes (TPAMI 2019 · similarity 0.91)
- Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs (CVPR 2018 · similarity 0.90)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (AAAI 2024 · similarity 0.88)
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.
