Research map / Image generation / Image restoration
PGMamba: A Physical Model-Guided Global Mamba for Underwater Image Enhancement
Zijun Tan, Chuan Fu, Tan Guo, Zhixiong Nan, Pengzhan Zhou, Xinggan Peng, Fulin Luo
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 global gate g to the SSM output matrix C (ablation) | SAGMamba · UIEB | PSNR: 23.75 -> 24.34 | Improved |
| add maxpool sparsification before ranking (ablation) | SAGMamba · UIEB | PSNR: 22.33 -> 24.34 | Improved |
| use SAGMamba instead of standard Mamba block (ablation) | PGMamba · UIEB | PSNR: 22.73 -> 24.34 | Improved |
| use SAGMamba instead of self-attention (ablation) | PGMamba · UIEB | PSNR: 23.05 -> 24.34 | Improved |
| inject global info g into A instead of omitting g (ablation) | SAGMamba · UIEB | PSNR: 23.75 -> 22.70 | Hurt |
| inject g into B or D instead of C (ablation) | SAGMamba · UIEB | PSNR: 24.34 -> 23.95 (B), 23.85 (D) | Hurt |
| use model weights p as global information instead of g (ablation) | SAGMamba · UIEB | PSNR: 24.34 -> 23.31 | Hurt |
| add PMGFFN module (ablation) | PGMamba · UIEB | PSNR: 23.82 -> 24.34 | Improved |
| add physical prior branch (PB) in PMGFFN (ablation) | PMGFFN · UIEB | PSNR: 23.89 -> 24.34 | Improved |
| use PMGFFN instead of ViT FFN (ablation) | PGMamba · UIEB | PSNR: 23.59 -> 24.34 | Improved |
| use PMGFFN instead of Restormer GDFN (ablation) | PGMamba · UIEB | PSNR: 23.66 -> 24.34 | Improved |
| PGMamba versus other methods on FID | PGMamba · UIEB | FID: 44.30 vs PUIE 35.65 | Mixed |
Closest papers by meaning
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.88)
- DRM-Net: Explicit Residual Modelling with Subaquatic Multi-Scale Context Fusion for Underwater Image Enhancement (AAAI 2026 · similarity 0.88)
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.87)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · similarity 0.86)
- Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion (CVPR 2024 · similarity 0.86)
- WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration (AAAI 2025 · similarity 0.85)
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.
