Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence
Occlusion is a critical issue that affects the accuracy for light field depth estimation. In the presence of occlusions, the photo-consistency property is broken, making ambiguity near occlusion areas. In this paper, we proposed using multi-orientation partial angular coherence to achieve accurate d...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8908798/ |
| _version_ | 1818427952539369472 |
|---|---|
| author | Zhenghua Guo Junlong Wu Xianfeng Chen Shuai Ma Licheng Zhu Ping Yang Bing Xu |
| author_facet | Zhenghua Guo Junlong Wu Xianfeng Chen Shuai Ma Licheng Zhu Ping Yang Bing Xu |
| author_sort | Zhenghua Guo |
| collection | DOAJ |
| description | Occlusion is a critical issue that affects the accuracy for light field depth estimation. In the presence of occlusions, the photo-consistency property is broken, making ambiguity near occlusion areas. In this paper, we proposed using multi-orientation partial angular coherence to achieve accurate depth estimation by which the occlusions are explicitly treated. Unlike previous approaches, the correspondence is partially measured along several lines with different directions. We show that depending on the occlusion edge orientation, the pixels along the occlusion orientation still preserve photo-consistency. By computing the partial angular coherence in four potential directions, we can obtain a sharp initial depth map. Since occlusions are precisely tackled, the outliers can be mostly removed by fast guided filtering on the cost volume. As a result, the depth accuracy at occlusion boundaries is greatly improved. The proposed method can obtain sharp transition edges at occlusion boundaries and has no requirement for extra edge information. Experimental results on a recent benchmark demonstrate that the proposed method outperforms the state-of-the-art algorithms in the accuracy metrics. Further experiments on real-world scenes also show the superior performance of the proposed method. |
| first_indexed | 2024-12-14T14:53:54Z |
| format | Article |
| id | doaj.art-1382f2803b454cc1ad33e02b7675cd8b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T14:53:54Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1382f2803b454cc1ad33e02b7675cd8b2022-12-21T22:57:02ZengIEEEIEEE Access2169-35362019-01-01716912316913210.1109/ACCESS.2019.29548928908798Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular CoherenceZhenghua Guo0https://orcid.org/0000-0003-1369-370XJunlong Wu1https://orcid.org/0000-0001-7733-9254Xianfeng Chen2https://orcid.org/0000-0003-0330-6032Shuai Ma3https://orcid.org/0000-0002-5829-9864Licheng Zhu4https://orcid.org/0000-0003-2103-8748Ping Yang5https://orcid.org/0000-0002-2243-6644Bing Xu6https://orcid.org/0000-0001-6391-5919Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaKey Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaKey Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaKey Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaKey Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaKey Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaKey Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, ChinaOcclusion is a critical issue that affects the accuracy for light field depth estimation. In the presence of occlusions, the photo-consistency property is broken, making ambiguity near occlusion areas. In this paper, we proposed using multi-orientation partial angular coherence to achieve accurate depth estimation by which the occlusions are explicitly treated. Unlike previous approaches, the correspondence is partially measured along several lines with different directions. We show that depending on the occlusion edge orientation, the pixels along the occlusion orientation still preserve photo-consistency. By computing the partial angular coherence in four potential directions, we can obtain a sharp initial depth map. Since occlusions are precisely tackled, the outliers can be mostly removed by fast guided filtering on the cost volume. As a result, the depth accuracy at occlusion boundaries is greatly improved. The proposed method can obtain sharp transition edges at occlusion boundaries and has no requirement for extra edge information. Experimental results on a recent benchmark demonstrate that the proposed method outperforms the state-of-the-art algorithms in the accuracy metrics. Further experiments on real-world scenes also show the superior performance of the proposed method.https://ieeexplore.ieee.org/document/8908798/Depth estimationlight fieldangular coherenceocclusion handling |
| spellingShingle | Zhenghua Guo Junlong Wu Xianfeng Chen Shuai Ma Licheng Zhu Ping Yang Bing Xu Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence IEEE Access Depth estimation light field angular coherence occlusion handling |
| title | Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence |
| title_full | Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence |
| title_fullStr | Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence |
| title_full_unstemmed | Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence |
| title_short | Accurate Light Field Depth Estimation Using Multi-Orientation Partial Angular Coherence |
| title_sort | accurate light field depth estimation using multi orientation partial angular coherence |
| topic | Depth estimation light field angular coherence occlusion handling |
| url | https://ieeexplore.ieee.org/document/8908798/ |
| work_keys_str_mv | AT zhenghuaguo accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence AT junlongwu accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence AT xianfengchen accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence AT shuaima accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence AT lichengzhu accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence AT pingyang accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence AT bingxu accuratelightfielddepthestimationusingmultiorientationpartialangularcoherence |