We propose to do this by first explicitly aligning the neighboring frames to the current frame using a convolutional neural network (CNN).
Since the number of HDR images for training is limited, we propose to train our system in two stages.
Image and Video Processing Graphics
In this paper, we address this problem using two video streams as input; an auxiliary video with high frame rate and low spatial resolution, providing temporal information, in addition to the standard main video with low frame rate and high spatial resolution.
We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration.
Experimental results show that our approach produces better results than the state-of-the-art DL and non-DL methods on various synthetic and real datasets both visually and numerically.
Given a 3 fps light field sequence and a standard 30 fps 2D video, our system can then generate a full light field video at 30 fps.