Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions

TL;DR

The paper tackles image quality degradation under complex illumination by proposing a unified framework that performs simultaneous enhancement and noise suppression. It introduces GDWGIF for accurate illumination estimation, structure-aware dual-illumination estimation, adaptive correction via gamma and Retinex-based reflection processing, and multi-exposure fusion to extend dynamic range. The approach preserves edges and details while suppressing noise, outperforming state-of-the-art methods on real-space and practical datasets according to NIQE, ARISM, and NIQMC metrics. The results demonstrate practical utility for vision-based measurements and remote sensing in challenging lighting environments.

Abstract

Under challenging light conditions, captured images often suffer from various degradations, leading to a decline in the performance of vision-based applications. Although numerous methods have been proposed to enhance image quality, they either significantly amplify inherent noise or are only effective under specific illumination conditions. To address these issues, we propose a novel framework for simultaneous enhancement and noise suppression under complex illumination conditions. Firstly, a gradient-domain weighted guided filter (GDWGIF) is employed to accurately estimate illumination and improve image quality. Next, the Retinex model is applied to decompose the captured image into separate illumination and reflection layers. These layers undergo parallel processing, with the illumination layer being corrected to optimize lighting conditions and the reflection layer enhanced to improve image quality. Finally, the dynamic range of the image is optimized through multi-exposure fusion and a linear stretching strategy. The proposed method is evaluated on real-world datasets obtained from practical applications. Experimental results demonstrate that our proposed method achieves better performance compared to state-of-the-art methods in both contrast enhancement and noise suppression.

Figures (13)

• Figure 1: An example of our proposed adjustment framework under complex illumination conditions. The gray distribution map and linear pixel mapping map are utilized to demonstrate the changes before and after adjustment.
• Figure 2: The schematic diagram illustrates the proposed framework for simultaneous image enhancement and noise suppression. Orange boxes: methods. Blue boxes: input or output images of each stage.
• Figure 3: Comparison of gradient map. Left: convolution gradient map. Right: edge-sensing gradient map.
• Figure 4: Adaptive window results. Left: the adaptive shape of the partial pixel window. Right: the change of pixels within the window.
• Figure 5: Comparison of four filters, the regularization parameter $\lambda$ is 0.1 and the window size is 7 $\times$ 7. (a) The input image. (b) GIF GIF filtered image. (c) WGIF WGIF filtered image. (d) EGIF EGIF filtered image. (e) The proposed GDWGIF filtered image.