Papers › A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing

A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing

8 Feb 2022arXiv:2202.04757archive 2025-07-28

Le-Anh Tran, Seokyong Moon, Dong-Chul Park

A novel Encoder-Decoder Network with Guided Transmission Map (EDN-GTM) for single image dehazing scheme is proposed in this paper. The proposed EDN-GTM takes conventional RGB hazy image in conjunction with its transmission map estimated by adopting dark channel prior as the inputs of the network. The proposed EDN-GTM utilizes U-Net for image segmentation as the core network and utilizes various modifications including spatial pyramid pooling module and Swish activation to achieve state-of-the-art dehazing performance. Experiments on benchmark datasets show that the proposed EDN-GTM outperforms most of traditional and deep learning-based image dehazing schemes in terms of PSNR and SSIM metrics. The proposed EDN-GTM furthermore proves its applicability to object detection problems. Specifically, when applied to an image preprocessing tool for driving object detection, the proposed EDN-GTM can efficiently remove haze and significantly improve detection accuracy by 4.73% in terms of mAP measure. The code is available at: https://github.com/tranleanh/edn-gtm.

Paper PDF Code

Code

tranleanh/edn-gtm officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decoder Image Dehazing Image Segmentation Nonhomogeneous Image Dehazing Object Detection SSIM Semantic Segmentation Single Image Dehazing object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Dehazing	Dense-Haze	EDN-GTM	PSNR	15.43	#5 of 5	Archive leaderboard	report
Image Dehazing	Dense-Haze	EDN-GTM	SSIM	0.5200	#5 of 5	Archive leaderboard	report
Image Dehazing	I-Haze	EDN-GTM	PSNR	22.90	#1 of 4	Archive leaderboard	report
Image Dehazing	I-Haze	EDN-GTM	SSIM	0.8270	#1 of 4	Archive leaderboard	report
Image Dehazing	O-Haze	EDN-GTM	PSNR	23.46	#6 of 7	Archive leaderboard	report
Image Dehazing	O-Haze	EDN-GTM	SSIM	0.8198	#6 of 7	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Average Pooling Batch Normalization Concatenated Skip Connection Convolution Max Pooling Pyramid Pooling Module ReLU Sigmoid Activation Spatial Pyramid Pooling U-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections