International Conference on Computer Vision, Theory and Applications (VISAPP 2017) |
| |
| Dehazing using Non-Local Regularization with Iso-Depth Neighbor-Fields |
| |
| |
| |
Incheol Kim |
|
Min H. Kim |
|
| |
|
|
|
|
| |
Korea Advanced Institute of Science and Technology (KAIST) |
|
| |
|
|
|
|
| |
 |
| |
Comparison of dehazing results using (a) regu- larization of haze using traditional MRFs commonly used in most of dehazing algorithms and (b) our regularization using MRFs with iso-depth NNFs (Insets: corresponding transmission maps). Our proposed method for single-image dehazing can propagate haze more effectively than tradi- tional regularization methods by inferring depth from NNFs in a hazy image. |
|
| |
|
|
| |
|
| |
Abstract |
| |
|
| |
Removing haze from a single image is a severely ill-posed problem due to the lack of the scene information. General dehazing algorithms estimate airlight initially using natural image statistics and then propagate the incompletely estimated airlight to build a dense transmission map, yielding a haze-free image. Propagating haze is different from other regularization problems, as haze is strongly correlated with depth according to the physics of light transport in participating media. However, since there is no depth information available in single-image dehazing, traditional regularization methods with a common grid random field often suffer from haze isolation artifacts caused by abrupt changes in scene depths. In this paper, to overcome the haze isolation problem, we propose a non-local regularization method by combining Markov random fields (MRFs) with nearest-neighbor fields (NNFs), based on our insightful observation that the NNFs searched in a hazy image associate patches at the similar depth, as local haze in the atmosphere is proportional to its depth. We validate that the proposed method can regularize haze effectively to restore a variety of natural landscape images, as demonstrated in the results. This proposed regularization method can be used separately with any other dehazing algorithms to enhance haze regularization.
|
| |
|
| |
|
| |
@InProceedings{KimKim:visapp:2017,
author = {Incheol Kim and Min H. Kim},
title = {Dehazing using Non-Local Regularization
with Iso-Depth Neighbor-Fields},
booktitle = {Proc. Int. Conf. Computer Vision,
Theory and Applications (VISAPP 2017)},
address = {Porto, Portugal},
year = {2017},
pages = {},
}
|
|
|
|
|
|
|
Hosted by Visual Computing Laboratory, School of Computing, KAIST.
|
 |
|
