Research map / Image generation / Image restoration
Zero-Shot Single Image Restoration Through Controlled Perturbation of Koschmieder's Model
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 |
|---|---|---|---|
| use controlled Koschmieder-model perturbation with transmission-relation and light-similarity losses (ablation) | zero-shot image dehazing · Single hazy image | Haze reduction | Helped |
| add Gray-world assumption loss (ablation) | zero-shot image restoration · Single hazy image | Color-cast reduction | Helped |
| add pure-white and pure-black saturation penalties (ablation) | zero-shot image restoration · Single hazy image | Pixel saturation prevention | Helped |
| use the proposed zero-shot framework instead of MSBDN | single-image dehazing · I-Haze | PSNR: 16.57 -> 16.79 | Helped |
| use the proposed zero-shot framework instead of MSBDN | single-image dehazing · O-Haze | PSNR: 16.83 -> 16.63 | Hurt |
| use the proposed zero-shot framework instead of Statistical | underwater image restoration · U45 | UIQM: 5.75 -> 4.97 | Hurt |
| use the proposed zero-shot framework instead of All-in-One | underwater image restoration · Challenging-60 | UIQM: 3.64 -> 3.81 | Helped |
| use the proposed zero-shot framework instead of All-in-One | underwater image restoration · Stereo | UIQM: 4.73 -> 3.84 | Hurt |
| use the proposed zero-shot framework instead of PR | low-light image enhancement · LOL | PSNR: 18.80 -> 17.50 | Hurt |
Closest papers by meaning
- Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual (CVPR 2025 · similarity 0.87)
- Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond) (CVPR 2025 · similarity 0.86)
- Masked Pre-training Enables Universal Zero-shot Denoiser (NeurIPS 2024 · similarity 0.86)
- Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework (NeurIPS 2025 · similarity 0.86)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (AAAI 2025 · similarity 0.86)
- From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective (CVPR 2025 · 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.