AOD-Net: All-in-One Dehazing Network

We proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level tasks on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN, we witness a large improvement of the object detection performance on hazy images.

Paper

B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng, “AOD-Net: All-in-One Dehazing Network”, In Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017. [PDF]

Download

[Code]

Note: If you could not download successfully, you could also find this code in github .

dataset

[training images] [original images]

Note: If you use this synthetic dataset, you should also cite NYU2 paper[bibtex].

Bibtex