CDAN: Convolutional dense attention-guided network for low-light image enhancement

TL;DR

The Convolutional Dense Attention-guided Network (CDAN) is introduced, a novel solution for enhancing low-light images that integrates an autoencoder-based architecture with convolutional and dense blocks, complemented by an attention mechanism and skip connections and refines color balance and contrast.

Abstract

Low-light images, characterized by inadequate illumination, pose challenges of diminished clarity, muted colors, and reduced details. Low-light image enhancement, an essential task in computer vision, aims to rectify these issues by improving brightness, contrast, and overall perceptual quality, thereby facilitating accurate analysis and interpretation. This paper introduces the Convolutional Dense Attention-guided Network (CDAN), a novel solution for enhancing low-light images. CDAN integrates an autoencoder-based architecture with convolutional and dense blocks, complemented by an attention mechanism and skip connections. This architecture ensures efficient information propagation and feature learning. Furthermore, a dedicated post-processing phase refines color balance and contrast. Our approach demonstrates notable progress compared to state-of-the-art results in low-light image enhancement, showcasing its robustness across a wide range of challenging scenarios. Our model performs remarkably on benchmark datasets, effectively mitigating under-exposure and proficiently restoring textures and colors in diverse low-light scenarios. This achievement underscores CDAN's potential for diverse computer vision tasks, notably enabling robust object detection and recognition in challenging low-light conditions.

Figures (13)

• Figure 1: The overall structure of the proposed CDAN. The model integrates autoencoder-based architecture with convolutional and dense blocks, attention modules, and skip connections, facilitating efficient information propagation and feature learning.
• Figure 2: Comparing deep learning-based state-of-the-art approaches on a low-light image from the LOL test dataset.
• Figure 3: Comparing deep learning-based state-of-the-art approaches on a low-light image from the LOL test dataset.
• Figure 4: Comparing deep learning-based state-of-the-art approaches on a low-light image from the LOL test dataset.
• Figure 5: Comparing deep learning-based state-of-the-art approaches on six low-light images from the ExDark dataset.