计算机科学
人工智能
稳健性(进化)
卷积神经网络
计算机视觉
水准点(测量)
特征(语言学)
亮度
地理
基因
光学
大地测量学
物理
哲学
语言学
化学
生物化学
作者
Hossein Shakibania,Sina Raoufi,Hassan Khotanlou
出处
期刊:Cornell University - arXiv
日期:2023-08-24
标识
DOI:10.48550/arxiv.2308.12902
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI