Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)

TL;DR

JUDE is a deep unrolling method that jointly addresses deblurring and low-light enhancement by integrating physical models, leading to superior results in night photography scenarios.

Contribution

The paper introduces a novel deep unrolling framework based on Retinex theory for simultaneous deblurring and low-light enhancement, incorporating modules for kernel estimation, brightness enhancement, and noise removal.

Findings

Outperforms existing methods quantitatively and qualitatively

Effective in handling real-world low-light blurry images

Demonstrates robustness across diverse datasets

Abstract

Low-light and blurring issues are prevalent when capturing photos at night, often due to the use of long exposure to address dim environments. Addressing these joint problems can be challenging and error-prone if an end-to-end model is trained without incorporating an appropriate physical model. In this paper, we introduce JUDE, a Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement, inspired by the image physical model. Based on Retinex theory and the blurring model, the low-light blurry input is iteratively deblurred and decomposed, producing sharp low-light reflectance and illuminance through an unrolling mechanism. Additionally, we incorporate various modules to estimate the initial blur kernel, enhance brightness, and eliminate noise in the final image. Comprehensive experiments on LOL-Blur and Real-LOL-Blur demonstrate that our method outperforms existing techniques both quantitatively and qualitatively.