Computational Light Field Generation Using Deep Nonparametric Bayesian Learning

Nan Meng, Xing Sun, Hayden Kwok-Hay So, Edmund Y. Lam

Abstract

In this paper, we present a deep nonparametric Bayesian method to synthesize a light field from a single image. Conventionally, light-field capture requires special optical architecture, and the gain in angular resolution often comes at the expense of a reduction in spatial resolution. Techniques for computationally generating the light field from a single image can be expanded further to a variety of applications, ranging from microscopy and materials analysis to vision-based robotic control and autonomous vehicles. We treat the light field as multiple sub-aperture views, and to compute the novel viewpoints, our model contains three major components. First, a convolutional neural network is used for predicting the depth probability map from the image. Second, a multi-scale feature dictionary is constructed within a multi-layer dictionary learning network. Third, the novel views are synthesized taking into account both the probabilistic depth map and the multi-scale feature dictionary. The experiments show that our method outperforms several state-of-the-art novel view synthesis methods in delivering good image resolution.
BibTeX
@inproceedings{meng2019computational,
  author = {Nan Meng and Xing Sun and Hayden Kwok-Hay So and Edmund Y. Lam},
  title = {{Computational Light Field Generation Using Deep Nonparametric Bayesian Learning}},
  booktitle = {IEEE Access},
  year = {2019},
  url = {https://openreview.net/forum?id=5YwLH4e4KLh},
}

Loading related content...

Figure