A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing
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.
PDF AbstractCode
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Image Dehazing | Dense-Haze | EDN-GTM | SSIM | 0.5200 | # 2 | |
PSNR | 15.43 | # 3 | ||||
Image Dehazing | I-Haze | EDN-GTM | SSIM | 0.8270 | # 2 | |
PSNR | 22.90 | # 1 | ||||
Nonhomogeneous Image Dehazing | NH-HAZE validation | EDN-GTM | PSNR | 20.24 | # 2 | |
SSIM | 0.7178 | # 1 | ||||
Image Dehazing | O-Haze | EDN-GTM | PSNR | 23.46 | # 3 | |
SSIM | 0.8198 | # 2 |