An All-in-One Network for Dehazing and Beyond
It addresses image quality degradation in hazy conditions for computer vision applications, offering an incremental improvement by simplifying the dehazing process and enhancing downstream tasks.
The paper tackles image dehazing by proposing AOD-Net, a lightweight CNN that directly generates clean images from a reformulated atmospheric scattering model, achieving superior performance in PSNR and SSIM metrics and improving object detection on hazy images when integrated with Faster R-CNN.
This paper 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 task performance 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 and training the joint pipeline from end to end, we witness a large improvement of the object detection performance on hazy images.