Encoder-Decoder Network with Guided Transmission Map: Architecture

TL;DR

This paper introduces EDN-GTM, a novel encoder-decoder network with guided transmission map for single image dehazing, achieving state-of-the-art results by integrating transmission maps with an enhanced U-Net architecture.

Contribution

The paper presents a new dehazing architecture that effectively combines transmission maps with an improved U-Net, demonstrating superior performance on benchmark datasets.

Findings

Achieves state-of-the-art PSNR and SSIM metrics

Effectively integrates transmission maps into the dehazing process

Provides extensive analysis of architectural choices

Abstract

An insight into the architecture of the Encoder-Decoder Network with Guided Transmission Map (EDN-GTM), a novel and effective single image dehazing scheme, is presented in this paper. The EDN-GTM takes a conventional RGB hazy image in conjunction with the corresponding transmission map estimated by the dark channel prior (DCP) approach as inputs of the network. The EDN-GTM adopts an enhanced structure of U-Net developed for dehazing tasks and the resulting EDN-GDM has shown state-of-the-art performances on benchmark dehazing datasets in terms of PSNR and SSIM metrics. In order to give an in-depth understanding of the well-designed architecture which largely contributes to the success of the EDN-GTM, extensive experiments and analysis from selecting the core structure of the scheme to investigating advanced network designs are presented in this paper.