Name
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. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ACCESS.2019.2900153 | IEEE ACCESS |
Keywords | Field | DocType |
Image reconstruction,convolutional neural network,deep learning,nonparametric Bayesian,light field imaging | Iterative reconstruction,Pattern recognition,Convolutional neural network,Computer science,Light field,Angular resolution,View synthesis,Artificial intelligence,Depth map,Probabilistic logic,Image resolution,Distributed computing | Journal |
Volume | ISSN | Citations |
7 | 2169-3536 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nan Meng | 1 | 5 | 2.10 |
| Sun Xing | 2 | 33 | 10.94 |
| Hayden K.-H. So | 3 | 247 | 36.22 |
| edmund y lam | 4 | 683 | 69.87 |