To address this major problem, we make a key observation that the process of synthesizing novel views requires changing the shading of the pixels based on the novel camera, and moving them to appropriate locations.
Instead, we train a generator for a neural material representation that is rendered with a learned relighting module to create arbitrarily lit RGB images; these are compared against real photos using a discriminator.
In this paper, we propose an approach for view-time interpolation of stereo videos.
Accurate facial landmark detection on wild images plays an essential role in human-computer interaction, entertainment, and medical applications.
To do this, we propose to encode the bidirectional flows into a coordinate-based network, powered by a hypernetwork, to obtain a continuous representation of the flow across time.
We propose to do this by first explicitly aligning the neighboring frames to the current frame using a convolutional neural network (CNN).
Ranked #2 on Video Denoising on CRVD
Since the number of HDR images for training is limited, we propose to train our system in two stages.
Inverse-Tone-Mapping 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.