Sorry, you need to enable JavaScript to visit this website.

Spatial and Angular Reconstruction of Light field Based on Deep Generative Networks

Citation Author(s):
Nan Meng, Tianjiao Zeng, Edmund Y. Lam
Submitted by:
Nan Meng
Last updated:
13 September 2019 - 9:14am
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Nan Meng
Paper Code:
2357
 

Light field (LF) cameras often have significant limitations in spatial and angular resolutions due to their design. Many techniques that attempt to reconstruct LF images at a higher resolution only consider either spatial or angular resolution, but not both. We propose a generative network using high-dimensional convolution to improve both aspects. Our experimental results on both synthetic and real-world data demonstrate that the proposed model outperforms existing state-of-the-art methods in terms of both peak signal-to-noise ratio (PSNR) and visual quality. The proposed method can also generate more realistic spatial details with better fidelity.

up
0 users have voted: