LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

Hao Sheng; Yebin Liu; Jingyi Yu; Gaochang Wu; Wei Xiong; Longzhao Guo; Yanlin Xie; Shuo Zhang; Song Chang; Youfang Lin; Wentao Chao; Xuechun Wang; Guanghui Wang; Fuqing Duan; Tun Wang; Da Yang; Zhenglong Cui; Sizhe Wang; Mingyuan Zhao; Qiong Wang; Qianyu Chen; Zhengyu Liang; Yingqian Wang; Jungang Yang; Xueting Yang; Junli Deng; Ruixuan Cong; Rongshan Chen

doi:10.1109/CVPRW59228.2023.00350

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

Hao Sheng
, Yebin Liu
, Jingyi Yu
, Gaochang Wu
, Wei Xiong
, Longzhao Guo
, Yanlin Xie
, Shuo Zhang
, Song Chang
, Youfang Lin
, Wentao Chao
, Xuechun Wang
, Guanghui Wang
, Fuqing Duan
, Tun Wang
, Da Yang
, Zhenglong Cui
, Sizhe Wang
, Mingyuan Zhao
, Qiong Wang

Qianyu Chen, Zhengyu Liang, Yingqian Wang, Jungang Yang, Xueting Yang, Junli Deng, Ruixuan Cong^*, Rongshan Chen^*

^*Corresponding author for this work

School of Computer Science and Engineering

Beihang Hangzhou Innovation Institute Yuhang
Macao Polytechnic University
Tsinghua University
ShanghaiTech University
Northeastern University China
Beijing Meet Yuan Co.,Ltd
Beijing Jiaotong University
Beijing Normal University
Toronto Metropolitan University
Beihang University
Zhejiang University of Technology
National University of Defense Technology
Communication University of China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Scopus citations

Abstract

This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.

Original language	English
Title of host publication	Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Publisher	IEEE Computer Society
Pages	3473-3485
Number of pages	13
ISBN (Electronic)	9798350302493
DOIs	https://doi.org/10.1109/CVPRW59228.2023.00350
State	Published - 2023
Event	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Canada Duration: 18 Jun 2023 → 22 Jun 2023

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2023-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Country/Territory	Canada
City	Vancouver
Period	18/06/23 → 22/06/23

Access to Document

10.1109/CVPRW59228.2023.00350

Cite this

Sheng, H., Liu, Y., Yu, J., Wu, G., Xiong, W., Guo, L., Xie, Y., Zhang, S., Chang, S., Lin, Y., Chao, W., Wang, X., Wang, G., Duan, F., Wang, T., Yang, D., Cui, Z., Wang, S., Zhao, M., ... Chen, R. (2023). LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 (pp. 3473-3485). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW59228.2023.00350

@inproceedings{324a7f490f6845c481ceca8a30f727ad,

title = "LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results",

abstract = "This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.",

author = "Hao Sheng and Yebin Liu and Jingyi Yu and Gaochang Wu and Wei Xiong and Longzhao Guo and Yanlin Xie and Shuo Zhang and Song Chang and Youfang Lin and Wentao Chao and Xuechun Wang and Guanghui Wang and Fuqing Duan and Tun Wang and Da Yang and Zhenglong Cui and Sizhe Wang and Mingyuan Zhao and Qiong Wang and Qianyu Chen and Zhengyu Liang and Yingqian Wang and Jungang Yang and Xueting Yang and Junli Deng and Ruixuan Cong and Rongshan Chen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 ; Conference date: 18-06-2023 Through 22-06-2023",

year = "2023",

doi = "10.1109/CVPRW59228.2023.00350",

language = "英语",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "3473--3485",

booktitle = "Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023",

address = "美国",

}

Sheng, H, Liu, Y, Yu, J, Wu, G, Xiong, W, Guo, L, Xie, Y, Zhang, S, Chang, S, Lin, Y, Chao, W, Wang, X, Wang, G, Duan, F, Wang, T, Yang, D, Cui, Z, Wang, S, Zhao, M, Wang, Q, Chen, Q, Liang, Z, Wang, Y, Yang, J, Yang, X, Deng, J, Cong, R & Chen, R 2023, LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results. in Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2023-June, IEEE Computer Society, pp. 3473-3485, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, Vancouver, Canada, 18/06/23. https://doi.org/10.1109/CVPRW59228.2023.00350

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results. / Sheng, Hao; Liu, Yebin; Yu, Jingyi et al.
Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society, 2023. p. 3473-3485 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - LFNAT 2023 Challenge on Light Field Depth Estimation

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

AU - Sheng, Hao

AU - Liu, Yebin

AU - Yu, Jingyi

AU - Wu, Gaochang

AU - Xiong, Wei

AU - Guo, Longzhao

AU - Xie, Yanlin

AU - Zhang, Shuo

AU - Chang, Song

AU - Lin, Youfang

AU - Chao, Wentao

AU - Wang, Xuechun

AU - Wang, Guanghui

AU - Duan, Fuqing

AU - Wang, Tun

AU - Yang, Da

AU - Cui, Zhenglong

AU - Wang, Sizhe

AU - Zhao, Mingyuan

AU - Wang, Qiong

AU - Chen, Qianyu

AU - Liang, Zhengyu

AU - Wang, Yingqian

AU - Yang, Jungang

AU - Yang, Xueting

AU - Deng, Junli

AU - Cong, Ruixuan

AU - Chen, Rongshan

PY - 2023

Y1 - 2023

N2 - This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.

AB - This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.

UR - https://www.scopus.com/pages/publications/85170828839

U2 - 10.1109/CVPRW59228.2023.00350

DO - 10.1109/CVPRW59228.2023.00350

M3 - 会议稿件

AN - SCOPUS:85170828839

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 3473

EP - 3485

BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

PB - IEEE Computer Society

Y2 - 18 June 2023 through 22 June 2023

ER -

Sheng H, Liu Y, Yu J, Wu G, Xiong W, Guo L et al. LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society. 2023. p. 3473-3485. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW59228.2023.00350

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this