Research map / Image generation / Image restoration
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
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 the model-free refinement stage after physics-based restoration (ablation) | Heavy Rain Image Restoration · Test 1 | PSNR: 20.05 -> 21.56 | Helped |
| add the model-free refinement stage after physics-based restoration (ablation) | Heavy Rain Image Restoration · Test 1 | SSIM: 0.779 -> 0.855 | Helped |
| add residue-channel guidance to decomposition instead of using no decomposition (ablation) | physics-based restoration stage · Test 1 | J PSNR: 10.87 -> 13.83 | Helped |
| add residue-channel guidance to decomposition instead of using no decomposition (ablation) | physics-based restoration stage · Test 1 | T PSNR: 14.95 -> 19.48 | Helped |
| add residue-channel guidance to decomposition instead of input-image guidance (ablation) | physics-based restoration stage · Test 1 | S PSNR: 23.42 -> 23.70 | No clear effect |
| add residue-channel guidance to decomposition instead of input-image guidance (ablation) | physics-based restoration stage · Test 1 | T PSNR: 15.85 -> 19.48 | Helped |
| add residue-channel guidance to decomposition instead of input-image guidance (ablation) | physics-based restoration stage · Test 1 | A error: 0.151 -> 0.150 | Helped |
| add decomposition to the physics-based stage (ablation) | Heavy Rain Image Restoration · Test 1 | J PSNR: 10.87 -> 13.83 | Helped |
Closest papers by meaning
- Singe Image Rain Removal with Unpaired Information: A Differentiable Programming Perspective (AAAI 2019 · similarity 0.93)
- Removing Rain From Single Images via a Deep Detail Network (CVPR 2017 · similarity 0.90)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.88)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.88)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · similarity 0.88)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.88)
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.