Research map / Image generation / Editing and style transfer
Recursive Copy and Paste GAN: Face Hallucination from Shaded Thumbnails
Yang Zhang, Ivor Wai-Hung Tsang, Yawei Luo, Changhui Hu, Xiaobo Lu, Xin 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 |
|---|---|---|---|
| add internal CPnet (ablation) | CPGAN · Multi-PIE | PSNR: 22.164 -> 24.639 | Improved |
| add internal CPnet (ablation) | CPGAN · Multi-PIE | SSIM: 0.693 -> 0.778 | Improved |
| add internal CPnet (ablation) | CPGAN · CelebA | PSNR: 21.441 -> 23.972 | Improved |
| add internal CPnet (ablation) | CPGAN · CelebA | SSIM: 0.578 -> 0.723 | Improved |
| add external CPnet (ablation) | CPGAN · Multi-PIE | PSNR: 21.925 -> 24.639 | Improved |
| add external CPnet (ablation) | CPGAN · Multi-PIE | SSIM: 0.680 -> 0.778 | Improved |
| add external CPnet (ablation) | CPGAN · CelebA | PSNR: 21.032 -> 23.972 | Improved |
| add external CPnet (ablation) | CPGAN · CelebA | SSIM: 0.536 -> 0.723 | Improved |
| use CPGAN instead of FHC (second best) in FH scenario | CPGAN · Multi-PIE (FH) | PSNR: 20.680 -> 24.639 | Improved |
| use CPGAN instead of FHC in FH scenario | CPGAN · CelebA (FH) | PSNR: 21.130 -> 23.972 | Improved |
| add identity similarity loss and structure similarity loss (ablation) | CPGAN · Qualitative faces | visual quality: blurred contours without them | Improved |
| add adversarial loss (ablation) | CPGAN · Qualitative faces | visual quality: sharper, more realistic | Improved |
Closest papers by meaning
- Copy and Paste GAN: Face Hallucination From Shaded Thumbnails (CVPR 2020 · similarity 0.99)
- Mask-Guided Portrait Editing With Conditional GANs (CVPR 2019 · similarity 0.86)
- Deep Cascaded Bi-Network for Face Hallucination (ECCV 2016 · similarity 0.86)
- Teacher-Student Adversarial Depth Hallucination To Improve Face Recognition (ICCV 2021 · similarity 0.86)
- Face Hallucination with Tiny Unaligned Images by Transformative Discriminative Neural Networks (AAAI 2017 · similarity 0.86)
- High-Resolution Face Swapping via Latent Semantics Disentanglement (CVPR 2022 · 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.
