Research map / Image generation / Image restoration
Uncertainty Inspired Underwater Image Enhancement
Zhenqi Fu, Wu Wang, Yue Huang, Xinghao Ding, Kai-Kuang 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 |
|---|---|---|---|
| increase MC sampling times from 1 to 20 (ablation) | PUIE-Net (MC) · UIEBD (test) | mean std-PSNR: 0.726 -> 0.175 | Improved |
| increase MC sampling times from 1 to 20 (ablation) | PUIE-Net (MC) · UIEBD (test) | mean std-SSIM: 0.008 -> 0.002 | Improved |
| increase sampling times from 20 to 50 (ablation) | PUIE-Net (MC) · UIEBD (test) | mean std-PSNR: 0.175 -> 0.166 | No clear effect |
| use MC averaging instead of maximum-probability sample (MP) (ablation) | PUIE-Net · UIEBD (test) | PSNR (dB): 21.05 -> 21.86 | Improved |
| use MC averaging instead of MP (ablation) | PUIE-Net · UIEBD (test) | SSIM: 0.854 -> 0.870 | Improved |
| use MC averaging instead of MP (ablation) | PUIE-Net · UIEBD (test) | MOS: 4.1 -> 4.2 | Improved |
| use MC averaging instead of MP (ablation) | PUIE-Net · UIEBD (test) | DeltaE: 10.26 -> 9.556 | Improved |
| use MC averaging instead of MP (ablation) | PUIE-Net · RUIE (quality subset) | NIQE: 4.555 -> 4.512 | Improved |
| probabilistic PUIE-Net (MC) versus best deterministic baseline Ucolor | PUIE-Net (MC) · UIEBD (test) | PSNR (dB): 21.65 -> 21.86 | Improved |
| probabilistic PUIE-Net (MC) versus Ucolor | PUIE-Net (MC) · UIEBD (test) | DeltaE: 8.646 -> 9.556 | Hurt |
| probabilistic PUIE-Net (MC) versus Histogram-Prior | PUIE-Net (MC) · RUIE (quality subset) | NIQE: 4.486 -> 4.512 | Hurt |
Closest papers by meaning
- Learning Underwater Image Enhancement Iteratively Without Reference Images (AAAI 2026 · similarity 0.89)
- HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image Enhancement (IJCV 2024 · similarity 0.89)
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.88)
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.88)
- 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 0.85)
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.
