Abstract
Acquisition of densely-sampled light fields (LFs) is challenging. In this paper, we develop a coarse-to-fine light field angular superresolution that reconstructs densely-sampled LFs from sparsely-sampled ones. Unlike most of other methods, which are limited by the regularity of sampling patterns, our method can flexibly deal with different scale factors with one model. Specifically, a coarse restoration on epipolar plane images (EPIs) with arbitrary angular resolution is performed and then a refinement with 3D convolutional neural networks (CNNs) on stacked EPIs. The subaperture images in LFs are synthesized first horizontally, then vertically, forming a pseudo 4DCNN. In addition, our method can handle large baseline light field without using geometry information, which means it is not constrained by Lambertian assumption. Experimental results over various light field datasets including large baseline LFs demonstrate the significant superiority of our method when compared with state-of-the-art ones.
Highlights
The light field (LF) encodes the distribution of light into a high-dimensional function, contains rich scene visual information [1, 2] and has a wide range of applications in various fields, such as image refocusing [3], 3D scene reconstruction [4], depth inference [5], and virtual augmented reality [6]
In our previous work [20], we proposed a learning-based model for reconstructing densely-sampled LFs via angular superresolution, which is achieved by using an image superresolution network on epipolar plane images (EPIs)
70 LF images captured by Lytro Illum camera were used for real-world scenes test, including 30 test scenes provided by Kalantari et al [17], 15 LF images from reflective [39] dataset, and 25 LF images from occlusions [39] dataset
Summary
The light field (LF) encodes the distribution of light into a high-dimensional function, contains rich scene visual information [1, 2] and has a wide range of applications in various fields, such as image refocusing [3], 3D scene reconstruction [4], depth inference [5], and virtual augmented reality [6]. In order to obtain high-quality views without ghosting effects, many studies have focused on dense sampling of LF [7]. Dense sampling of LF means great acquisition difficulties. Light field cameras, such as multicamera arrays and light field racks etc. [8], are bulky and expensive in hardware. The introduction of commercial and industrial light field cameras such as Lytro [9] and RayTrix [10] has brought light field imaging into a new era. Due to the limited resolution of the sensor, a trade-off must be made between spatial resolution and angular resolution
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
