This thesis discusses approaches and techniques to convert Sparsely-
Sampled Light Fields (SSLFs) into Densely-Sampled Light Fields (DSLFs),
which can be used for visualization on 3DTV and Virtual Reality (VR) de-
vices. Exemplarily, a movable 1D large-scale light field acquisition system
for capturing SSLFs in real-world environments is evaluated. This system
consists of 24 sparsely placed RGB cameras and two Kinect V2 sensors.
The real-world SSLF data captured with this setup can be leveraged to
reconstruct real-world DSLFs. To this end, three challenging problems
require to be solved for this system: (i) how to estimate the rigid trans-
formation from the coordinate system of a Kinect V2 to the coordinate
system of an RGB camera; (ii) how to register the two Kinect V2 sensors
with a large displacement; (iii) how to reconstruct a DSLF from a SSLF
with moderate and large disparity ranges.
To overcome these three challenges, we propose: (i) a novel self-
calibration method, which takes advantage of the geometric constraints
from the scene and the cameras, for estimating the rigid transformations
from the camera coordinate frame of one Kinect V2 to the camera coordi-
nate frames of 12-nearest RGB cameras; (ii) a novel coarse-to-fine approach
for recovering the rigid transformation from the coordinate system of one
Kinect to the coordinate system of the other by means of local color and
geometry information; (iii) several novel algorithms that can be categorized
into two groups for reconstructing a DSLF from an input SSLF, including
novel view synthesis methods, which are inspired by the state-of-the-art
video frame interpolation algorithms, and Epipolar-Plane Image (EPI) in-
painting methods, which are inspired by the Shearlet Transform (ST)-based
DSLF reconstruction approaches.
Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network