Research map / Image generation / Editing and style transfer
SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Control
Xiaofeng Cong, Yu-Xin Zhang, Hao Shen, Yeying Jin, Junming Hou, Jie Gui
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 semi-supervised training with real underwater images (ablation) | SDUIE-Quant · UCCS | URANKER: 2.204 -> 2.481 | Improved |
| add physics-based image synthesis instead of UIEB training data (ablation) | SDUIE-Quant · UCCS | UIQM: 4.152 -> 5.351 | Improved |
| add adversarial losses (ablation) | SDUIE-Quant · UCCS | URANKER: 1.771 -> 2.481 | Improved |
| add adversarial losses (ablation) | SDUIE-Quant · UCCS | UCIQE: 0.559 -> 0.563 | No clear effect |
| increase fusion factor alpha from 0 to 1 (ablation) | SDUIE-Quant · UCCS | UIQM: 1.501 -> 5.351 | Improved |
| increase enhancement level prompt from one to ten (ablation) | SDUIE-Text · EUVP | UIQM: 2.659 -> 4.728 | Improved |
| use spherical instead of linear LoRA interpolation (ablation) | SDUIE-Quant · visual, alpha=0.6 | visual quality | Improved |
| change the prompt template (T0 to T5) (ablation) | SDUIE-Text · U45 | UIQM: 4.991 vs 4.916-4.986 | No clear effect |
| construct prompt set with other LLMs (ablation) | SDUIE-Text · Challenge-60 | UIQM: 4.744 and 4.749 | No clear effect |
| raise enhancement level (ablation) | SDUIE-Quant · UCCS | UCIQE: 0.488 -> 0.563 | Mixed |
Closest papers by meaning
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.89)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · similarity 0.87)
- UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement (CVPR 2024 · similarity 0.87)
- Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement (AAAI 2024 · similarity 0.86)
- WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration (AAAI 2025 · 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.
