Computer Vision, Imaging and Computer Graphics - Theory and Applications, 2019
A Revised Selected Paper presented at International Conference, VISIGRAPP 2017
|
| |
| Non-local Haze Propagation with an Iso-Depth Prior |
| |
| |
| |
Incheol Kim |
|
Min H. Kim |
|
| |
|
|
|
|
| |
Korea Advanced Institute of Science and Technology (KAIST) |
|
| |
|
|
|
|
| |
 |
| |
Comparison of dehazing results using (a) regularization of haze using traditional MRFs commonly used in state-of-the-art dehazing algorithms [3–5] and (b) our regu- larization using MRFs with iso-depth NNFs (Insets: corresponding transmission maps). The proposed method for single-image dehazing can propagate haze more effectively than traditional regularization methods by inferring depth from NNFs in a hazy image. Images courtesy of Kim and Kim [1]. |
|
| |
|
|
| |
|
| |
Abstract |
| |
|
| |
The primary challenge for removing haze from a single image is lack of decomposition cues between the original light transport and airlight scattering in a scene. Many dehazing algorithms start from an assumption on natural image statistics to estimate airlight from sparse cues. The sparsely estimated airlight cues need to be propagated accord- ing to the local density of airlight in the form of a transmission map, which allows us to obtain a haze-free image by subtracting airlight from the hazy input. Traditional airlight-propagation methods rely on ordi- nary regularization on a grid random field, which often results in iso- lated haze artifacts when they fail in estimating local density of airlight properly. In this work, we propose a non-local regularization method for dehazing by combining Markov random fields (MRFs) with nearest- neighbor fields (NNFs) extracted from the hazy input using the Patch- Match algorithm. Our method starts from the insightful observation that the extracted NNFs can associate pixels at the similar depth. Since regional haze in the atmosphere is correlated with its depth, we can allow propagation across the iso-depth pixels with the MRF-based regulariza- tion problem with the NNFs. Our results validate how our method can restore a wide range of hazy images of natural landscape clearly without suffering from haze isolation artifacts. Also, our regularization method is directly applicable to various dehazing methods.
|
| |
|
| |
|
| |
@InProceedings{dehazing:ccis:2019,
author ="Kim, Incheol and Kim, Min H.",
title ="Non-local Haze Propagation with an Iso-Depth Prior",
booktitle="Computer Vision, Imaging and Computer Graphics
-- Theory and Applications",
year ="2019",
publisher="Springer International Publishing",
pages ="213--238",
isbn ="978-3-030-12209-6"
}
|
|
|
|
|
|
|
Hosted by Visual Computing Laboratory, School of Computing, KAIST.
|
 |
|
