Research map / Image generation / Super-resolution
Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance
Wenjie Li, Jinglei Shi, Jin Han, Heng Guo, Zhanyu Ma
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 diffusion-learned latent priors (ablation) | DHGM · Raindrop | PSNR: 25.41 -> 26.05 | Improved |
| learn priors with diffusion instead of CNN encoder (ablation) | DHGM · Raindrop | PSNR: 25.63 -> 26.05 | Improved |
| estimate priors in 1D latent space instead of feature maps (ablation) | DHGM diffusion · Raindrop | PSNR: 24.73 -> 26.05 | Improved |
| add guided filter (MR) (ablation) | DHGM · Raindrop | PSNR: 26.48 -> 26.82 | Improved |
| add high-pass filter (TC) (ablation) | DHGM · Raindrop | PSNR: 26.51 -> 26.82 | Improved |
| add both guided and high-pass filters (ablation) | DHGM · Raindrop | PSNR: 26.11 -> 26.82 | Improved |
| add cross-attention for feature fusion (ablation) | DHGM · Raindrop | PSNR: 26.73 -> 26.82 | Improved |
| joint DHGM vs cascading deraining and SR | DHGM · RainDS-Syn-Rain (x2) | PSNR: 27.23 -> 31.28 | Improved |
| joint DHGM vs best fine-tuned baseline | DHGM · RainDS-Syn-Rain (x2) | PSNR: 29.94 -> 31.28 | Improved |
| DHGM vs cascades on real raindrop set | DHGM · Raindrop (x2) | DISTS: 0.1378 vs 0.1385 (SR->Histoformer) | Mixed |
Closest papers by meaning
- BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution (AAAI 2025 · similarity 0.87)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.86)
- One-Step Effective Diffusion Network for Real-World Image Super-Resolution (NeurIPS 2024 · similarity 0.86)
- MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery (NeurIPS 2025 · similarity 0.86)
- Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs (NeurIPS 2024 · similarity 0.86)
- Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model (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.
