An All-in-One Network for Dehazing and Beyond
release_3zegktufxvffpli254tr64fppq
by
Boyi Li and Xiulian Peng and Zhangyang Wang and Jizheng Xu and Dan
Feng
2017
Abstract
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.
In text/plain
format
Archived Files and Locations
application/pdf 7.2 MB
file_pijxchzbavconajzwos2ejp2qa
|
arxiv.org (repository) web.archive.org (webarchive) |
1707.06543v1
access all versions, variants, and formats of this works (eg, pre-prints)