Home / Research Library / U-Shape Transformer for Underwater Image Enhanceme...
🤖 Artificial Intelligence OpenAlex

U-Shape Transformer for Underwater Image Enhancement

📅 January 1, 2023 👤 Lintao Peng, Chunli Zhu, Liheng Bian 📖 IEEE Transactions on Image Processing 📊 716 citations

🤖 Plain-English Summary

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The extensive experiments on available datasets validate the advanced performance of the reported technique with more than 2dB superiority.

🔑 Key Findings

  • The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images.
  • Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement.
  • In this work, we built a large scale underwater image (LSUI) dataset, which covers more abundant underwater scenes and better visual quality reference images than existing underwater datasets.

💡 Why This Matters

This research advances how AI systems learn, reason, and solve problems — with direct implications for automation and scientific discovery.

Read the full paper
Access the original peer-reviewed research via OpenAlex.

View on DOI ↗

📋 Article Details

Category 🤖 Artificial Intelligence
Published Jan 01, 2023
Journal IEEE Transactions on Image Processing
Authors Lintao Peng, Chunli Zhu, Liheng Bian
DOI 10.1109/tip.2023.3276332
Citations 716
Source OpenAlex

More 🤖 Artificial Intelligence Research