Research map / Image generation / Image restoration
Deblurring by Realistic Blurring
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 BGAN-generated blurry images during fine-tuning (ablation) | DBGAN · GOPRO_Large | PSNR: 30.43 -> 31.10 | Helped |
| Add BGAN-generated blurry images during fine-tuning (ablation) | DBGAN · GOPRO_Large | SSIM: 0.9372 -> 0.9424 | Helped |
| Replace traditional adversarial loss with relativistic deblur loss (ablation) | DBGAN · Image deblurring; qualitative ablation | perceptual quality | Helped |
| Add BGAN-generated blurry images during fine-tuning (ablation) | DBGAN · Image deblurring; qualitative ablation | perceptual quality | Helped |
| Use DBGAN(+) instead of Gao et al. | GOPRO_Large deblurring · GOPRO_Large | PSNR: 30.92 -> 31.10 | Helped |
| Use DBGAN(+) instead of Gao et al. | GOPRO_Large deblurring · GOPRO_Large | SSIM: 0.9421 -> 0.9424 | Helped |
Closest papers by meaning
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains (CVPR 2024 · similarity 0.89)
- Exploiting Deblurring Networks for Radiance Fields (CVPR 2025 · similarity 0.89)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.88)
- Unsupervised Blind Image Deblurring Based on Self-Enhancement (CVPR 2024 · similarity 0.88)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.87)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 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.