DehazeNet: An End-to-End System for Single Image Haze Removal
South China University of Technology · Centre for Quantum Computation and Communication Technology · +1 more institution
Abstract
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 network-based deep architecture, whose layers are specially designed to embody the established assumptions/priors in image dehazing. Specifically, the layers…
Citation impact
- FWCI
- 92.75
- Percentile
- 100%
- References
- 59
Authors
5- BCBolun CaiCorresponding
South China University of Technology
- XXXiangmin Xu
South China University of Technology
- KJKui Jia
South China University of Technology
- CQChunmei Qing
South China University of Technology
- DTDacheng Tao
Centre for Quantum Computation and Communication Technology, University of Technology Sydney
Topics & keywords
- End-to-end principle
- Computer science
- Computer vision
- Image processing
- Artificial intelligence
- Haze
- Image (mathematics)