文件列表:

boxfilter.m (904, 2017-04-05)
convConst.cpp (11527, 2017-04-05)
convConst.mexw64 (29184, 2017-04-05)
convMax.m (2318, 2017-04-05)
convolution.m (772, 2017-04-05)
data (0, 2018-03-26)
data\canyon.png (863895, 2017-04-05)
data\girls.jpg (168171, 2017-04-05)
data\gugong.bmp (720056, 2017-04-05)
data\man.png (372850, 2017-04-05)
data\ranges.png (760696, 2017-04-05)
dehaze.mat (31902, 2017-04-05)
demo.m (133, 2018-03-07)
guidedfilter.m (931, 2017-04-05)
run_cnn.m (1322, 2017-04-05)
sse.hpp (3125, 2017-04-05)
wrappers.hpp (1573, 2017-04-05)
备注：单图像.txt (0, 2018-03-26)

# DehazeNet: An End-to-End System for Single Image Haze Removal Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, Dacheng Tao ### Introduction Single image haze removal is a challenging ill-posed problem. Existing methods use various constraints/priors to get plausible dehazing solutions. The key to achieve haze removal is to estimate a medium transmission map for an input hazy image. In this paper, we propose a trainable end-to-end system called DehazeNet, for medium transmission estimation. DehazeNet takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model. DehazeNet adopts Convolutional Neural Networks (CNN) based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, layers of Maxout units are used for feature extraction, which can generate almost all haze-relevant features. We also propose a novel nonlinear activation function in DehazeNet, called Bilateral Rectified Linear Unit (BReLU), which is able to improve the quality of recovered haze-free image. We establish connections between components of the proposed DehazeNet and those used in existing methods. Experiments on benchmark images show that DehazeNet achieves superior performance over existing methods, yet keeps efficient and easy to use. If you use these codes in your research, please cite: @article{cai2016dehazenet, author = {Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing and Dacheng Tao}, title={DehazeNet: An End-to-End System for Single Image Haze Removal}, journal={IEEE Transactions on Image Processing}, year={2016}, volume={25}, number={11}, pages={5187-51***}, }

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：