Research map / Image generation / Autoregressive and latent generation
United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
Wenda Zhao, Fei Wei, You He, Huchuan Lu
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 three rounds of mutual adversarial promotion (Gws O3) to single detection (ablation) | Gws · CUHK defocus detection | Fmax: 0.785 -> 0.831 | Improved |
| add three rounds of mutual adversarial promotion (Gws O3) to single detection (ablation) | Gws · CUHK defocus detection | MAE: 0.173 -> 0.125 | Improved |
| add three rounds of mutual adversarial promotion (Gws O3) to single detection (ablation) | Gws · DUT defocus detection | Fmax: 0.679 -> 0.722 | Improved |
| second optimization round of Gws after the first (ablation) | Gws · DUT defocus detection | Fmax: 0.696 -> 0.682 | Mixed |
| add three rounds of mutual promotion (Gsr O3) to single deblurring (ablation) | Gsr · DP dataset deblurring | PSNR: 22.02 -> 25.71 | Improved |
| add self-reference by directly combining focused and defocused images (DC-GAN) (ablation) | U-GAN · DP dataset deblurring | PSNR: 22.02 -> 24.16 | Improved |
| add UFAT instead of directly combining focused and defocused images (ablation) | DC-GAN · DP dataset deblurring | PSNR: 24.16 -> 25.71 | Improved |
| add UFAT instead of concatenating intermediate deep features (ablation) | CDF-GAN · DP dataset deblurring | PSNR: 24.80 -> 25.71 | Improved |
| add local-contrast blur prior L1 loss to adversarial supervision of Gws (ablation) | Gws · defocus detection | detection quality | Improved |
| replace fully-supervised KPAC with the weakly-supervised proposed model | KPAC · DP dataset deblurring | PSNR: 26.51 -> 25.71 | Hurt |
| use the proposed method instead of SGNet | SGNet · CUHK defocus detection | MAE: 0.199 -> 0.125 | Improved |
Closest papers by meaning
- Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild (AAAI 2023 · similarity 0.93)
- Self-Generated Defocus Blur Detection via Dual Adversarial Discriminators (CVPR 2021 · similarity 0.92)
- DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features (CVPR 2019 · similarity 0.92)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.90)
- Prior and Prediction Inverse Kernel Transformer for Single Image Defocus Deblurring (AAAI 2024 · similarity 0.89)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 2025 · 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.
