Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)
This addresses image quality issues in low-light photography, but it is incremental as it builds on existing physical models and unrolling mechanisms.
The paper tackles the joint problem of deblurring and low-light image enhancement in night photography by proposing JUDE, a deep joint unrolling method inspired by physical models like Retinex theory, which outperforms existing techniques on datasets such as LOL-Blur and Real-LOL-Blur.
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.