Depth Estimation From a Light Field Image Pair With a Generative Model
In this paper, we propose a novel method to estimate the disparity maps from a light field image pair captured by a pair of light field cameras. Our method integrates two types of critical depth cues, which are separately inferred from the epipolar plane images and binocular stereo vision into a glo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8620996/ |
| _version_ | 1818557129365127168 |
|---|---|
| author | Tao Yan Fan Zhang Yiming Mao Hongbin Yu Xiaohua Qian Rynson W. H. Lau |
| author_facet | Tao Yan Fan Zhang Yiming Mao Hongbin Yu Xiaohua Qian Rynson W. H. Lau |
| author_sort | Tao Yan |
| collection | DOAJ |
| description | In this paper, we propose a novel method to estimate the disparity maps from a light field image pair captured by a pair of light field cameras. Our method integrates two types of critical depth cues, which are separately inferred from the epipolar plane images and binocular stereo vision into a global solution. At the same time, in order to produce highly accurate disparity maps, we adopt a generative model, which can estimate a light field image only with the central subaperture view and corresponding hypothesized disparity map. The objective function of our method is formulated to minimize two energy terms/differences. One is the difference between the two types of previously extracted disparity maps and the target disparity maps, directly optimized in the gray-scale disparity space. The other indicates the difference between the estimated light field images and the input light field images, optimized in the RGB color space. Comprehensive experiments conducted on real and virtual scene light field image pairs demonstrate the effectiveness of our method. |
| first_indexed | 2024-12-13T23:55:56Z |
| format | Article |
| id | doaj.art-b118fa90e96146d581463e6a0c387674 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T23:55:56Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b118fa90e96146d581463e6a0c3876742022-12-21T23:26:33ZengIEEEIEEE Access2169-35362019-01-017127681277810.1109/ACCESS.2019.28933548620996Depth Estimation From a Light Field Image Pair With a Generative ModelTao Yan0https://orcid.org/0000-0002-9162-8551Fan Zhang1Yiming Mao2Hongbin Yu3Xiaohua Qian4Rynson W. H. Lau5Jiangsu Key Laboratory of Media Design and Software Technology, School of Digital Media, Jiangnan University, Jiangsu, ChinaJiangsu Key Laboratory of Media Design and Software Technology, School of Digital Media, Jiangnan University, Jiangsu, ChinaJiangsu Key Laboratory of Media Design and Software Technology, School of Digital Media, Jiangnan University, Jiangsu, ChinaJiangsu Key Laboratory of Media Design and Software Technology, School of Digital Media, Jiangnan University, Jiangsu, ChinaInstitute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Computer Science, City University of Hong Kong, Hong KongIn this paper, we propose a novel method to estimate the disparity maps from a light field image pair captured by a pair of light field cameras. Our method integrates two types of critical depth cues, which are separately inferred from the epipolar plane images and binocular stereo vision into a global solution. At the same time, in order to produce highly accurate disparity maps, we adopt a generative model, which can estimate a light field image only with the central subaperture view and corresponding hypothesized disparity map. The objective function of our method is formulated to minimize two energy terms/differences. One is the difference between the two types of previously extracted disparity maps and the target disparity maps, directly optimized in the gray-scale disparity space. The other indicates the difference between the estimated light field images and the input light field images, optimized in the RGB color space. Comprehensive experiments conducted on real and virtual scene light field image pairs demonstrate the effectiveness of our method.https://ieeexplore.ieee.org/document/8620996/Light fielddepth estimationdisparity mapepipolar plane imagestereo matchinggenerative model |
| spellingShingle | Tao Yan Fan Zhang Yiming Mao Hongbin Yu Xiaohua Qian Rynson W. H. Lau Depth Estimation From a Light Field Image Pair With a Generative Model IEEE Access Light field depth estimation disparity map epipolar plane image stereo matching generative model |
| title | Depth Estimation From a Light Field Image Pair With a Generative Model |
| title_full | Depth Estimation From a Light Field Image Pair With a Generative Model |
| title_fullStr | Depth Estimation From a Light Field Image Pair With a Generative Model |
| title_full_unstemmed | Depth Estimation From a Light Field Image Pair With a Generative Model |
| title_short | Depth Estimation From a Light Field Image Pair With a Generative Model |
| title_sort | depth estimation from a light field image pair with a generative model |
| topic | Light field depth estimation disparity map epipolar plane image stereo matching generative model |
| url | https://ieeexplore.ieee.org/document/8620996/ |
| work_keys_str_mv | AT taoyan depthestimationfromalightfieldimagepairwithagenerativemodel AT fanzhang depthestimationfromalightfieldimagepairwithagenerativemodel AT yimingmao depthestimationfromalightfieldimagepairwithagenerativemodel AT hongbinyu depthestimationfromalightfieldimagepairwithagenerativemodel AT xiaohuaqian depthestimationfromalightfieldimagepairwithagenerativemodel AT rynsonwhlau depthestimationfromalightfieldimagepairwithagenerativemodel |