Depth from a Light Field Image with Learning-Based Matching Costs

One of the core applications of light field imaging is depth estimation. To acquire a depth map, existing approaches apply a single photo-consistency measure to an entire light field. However, this is not an optimal choice because of the non-uniform light field degradations produced by limitations i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2019-02, Vol.41 (2), p.297-310
Main Authors: Jeon, Hae-Gon, Park, Jaesik, Choe, Gyeongmin, Park, Jinsun, Bok, Yunsu, Tai, Yu-Wing, Kweon, In So
Format: Article
Language:English
Subjects:
3D reconstruction
aberration correction
Benchmarks
Cameras
Chlorophyll
Computational photography
Consistency
Degradation
depth estimation
Electrons
Estimation
Field cameras
Lenses
Light
light field imaging
Photodegradation
Reliability
State of the art
Training
Vignetting
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the core applications of light field imaging is depth estimation. To acquire a depth map, existing approaches apply a single photo-consistency measure to an entire light field. However, this is not an optimal choice because of the non-uniform light field degradations produced by limitations in the hardware design. In this paper, we introduce a pipeline that automatically determines the best configuration for photo-consistency measure, which leads to the most reliable depth label from the light field. We analyzed the practical factors affecting degradation in lenslet light field cameras, and designed a learning based framework that can retrieve the best cost measure and optimal depth label. To enhance the reliability of our method, we augmented an existing light field benchmark to simulate realistic source dependent noise, aberrations, and vignetting artifacts. The augmented dataset was used for the training and validation of the proposed approach. Our method was competitive with several state-of-the-art methods for the benchmark and real-world light field datasets.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2018.2794979