Research map / Image generation / Editing and style transfer
Exploiting Semantics for Face Image Deblurring
Ziyi Shen, Wei‐Sheng Lai, Tingfa Xu, Jan Kautz, Ming–Hsuan Yang
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 ground-truth semantic labels as input (ablation) | coarse deblurring network G · Helen | PSNR: 24.85 -> 25.85 | Improved |
| extract labels from coarse deblurred image instead of blurred image (ablation) | fine deblurring with parsing · Helen | PSNR: 25.32 -> 25.48 | Improved |
| extract labels from coarse deblurred image instead of blurred image (ablation) | face parsing network · Helen | parsing F-score: 0.615 -> 0.628 | Improved |
| add equal-weight local structural loss (ablation) | content-loss fine network · Helen | PSNR: 25.48 -> 25.72 | Improved |
| use adaptive instead of equal weights in local structural loss (ablation) | content-loss fine network · Helen | PSNR: 25.72 -> 25.80 | Improved |
| use adaptive instead of equal weights in local structural loss (ablation) | content-loss fine network · CelebA | SSIM: 0.869 -> 0.874 | Improved |
| train stage-by-stage plus joint fine-tuning instead of from scratch (ablation) | full three-network model · Helen | PSNR: 24.74 -> 25.92 | Improved |
| add perceptual (VGG) loss (ablation) | full model · Helen | PSNR: 25.92 -> 26.28 | Improved |
| add adversarial loss on top of perceptual loss (ablation) | full model · Helen | SSIM: 0.877 -> 0.876 | No clear effect |
| enlarge first conv kernel from 5x5 to 11x11 (ablation) | deblurring networks · Helen | PSNR: 25.63 -> 25.80 | Improved |
| enlarge first conv kernel from 11x11 to 13x13 (ablation) | deblurring networks · Helen | PSNR: 25.80 -> 25.80 | No clear effect |
| add a second fine deblurring stage (ablation) | full model · Helen | PSNR: 25.80 -> 25.87 | No clear effect |
Closest papers by meaning
- Deep Semantic Face Deblurring (CVPR 2018 · similarity 0.98)
- Learning to Deblur Face Images via Sketch Synthesis (AAAI 2020 · similarity 0.92)
- Learning to Deblur Images with Exemplars (TPAMI 2018 · similarity 0.92)
- Deep Image Deblurring: A Survey (IJCV 2022 · similarity 0.92)
- Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement (IJCV 2019 · similarity 0.91)
- Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration (CVPR 2024 · 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.
