Lightweight Encoder-Decoder Network for Single-Image Dehazing

Abstract

Images captured in hazy environment are often degraded, thereby impacting several applications of computer vision, like image segmentation, classification, object recognition, and many others. Accordingly, various techniques and algorithms for image dehazing were developed over the years - from old days traditional to the recent deep learning methods. Although deep learning technology have been proved to be better performing than the traditional methods, they are plagued by several drawbacks like high computational demand, limiting their usage for real-time applications. In view of this, here we develop a lightweight encoder-decoder network (LED-Net) for single-image haze removal in real-time using deep learning technology. To make it lightweight, we incorporate the depth-wise convolution in each convolution block. The performance of LED-Net is assessed on the basis of quantitative performance metrics, viz., PSNR and SSIM), qualitative analysis (visual quality), and real-time performance metrics such as inference time and throughput. Results obtained in our experiments show that, in comparison to some other previous state-of-the-art methods, our model offers a good compromise between output image quality and architectural complexity.