PIC-UIE: Predicting Image-Adaptive Corrections for Lightweight Underwater Image Enhancement

2026-09-27

AI Summary

This study addresses the challenges of parameter redundancy, deployment difficulty, and color-space coupling in underwater image enhancement models by proposing a lightweight "predict-execute" framework. Instead of dense pixel reconstruction, this method employs structured correction prediction: it analyzes RGB thumbnails to perform nonlinear luminance-chrominance decoupled correction on the original image within the YCbCr color space, while introducing depth-map regularization to supervise training. With only 9K parameters, the model achieves high PSNR and SSIM metrics and attains an inference speed of 55 FPS at 4K resolution, effectively balancing enhancement accuracy with real-time performance.

Abstract

Underwater image enhancement (UIE) aims to restore visibility, color fidelity, and structural detail from images degraded by wavelength-dependent attenuation and backscatter. State-of-the-art UIE methods often rely on large backbones and dense image-to-image prediction, limiting their practicality for edge deployment. Moreover, operating entirely in a single color space couples degradation estimation with luminance and chroma correction. To address these challenges, we propose PIC-UIE, a lightweight predictor--executor framework that predicts image-adaptive corrections from a fixed $256\times256$ RGB thumbnail and applies them to the native-resolution input in the YCbCr color space. The predictor produces seven outputs, organized into spatial correction, nonlinear luminance and coupled chroma mapping, and image-level color calibration. A depth map regularizes the transmission proxy during training, whereas inference uses only the RGB input. With 9,486 parameters and 0.094 GFLOPs at $256\times256$, PIC-UIE achieves 24.137 dB PSNR and 0.9216 SSIM on UIEB-90 and 21.320 dB PSNR on zero-shot LSUI. It further processes native 4K images at 55.0 FPS under the comparison protocol. These results show that structured correction prediction provides an effective and practical alternative to dense RGB reconstruction for underwater image enhancement.

Problem

• Underwater Image Enhancement
• Lightweight Model
• Edge Deployment
• Color Space Coupling

Innovation

• Underwater Image Enhancement
• Lightweight Framework
• Predictor-Executor Architecture
• Image-Adaptive Corrections
• YCbCr Color Space