Inference-Reconstruction Variational Autoencoder for Light Field Image Reconstruction

Han, Kang, and Xiang, Wei (2022) Inference-Reconstruction Variational Autoencoder for Light Field Image Reconstruction. IEEE Transactions on Image Processing, 31. pp. 5629-5644.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/TIP.2022.3197976
 
1


Abstract

Light field cameras can capture the radiance and direction of light rays by a single exposure, providing a new perspective to photography and 3D geometry perception. However, existing sub-aperture based light field cameras are limited by their sensor resolution to obtain high spatial and angular resolution images simultaneously. In this paper, we propose an inference-reconstruction variational autoencoder (IR-VAE) to reconstruct a dense light field image out of four corner reference views in a light field image. The proposed IR-VAE is comprised of one inference network and one reconstruction network, where the inference network infers novel views from existing reference views and viewpoint conditions, and the reconstruction network reconstructs novel views from a latent variable that contains the information of reference views, novel views, and viewpoints. The conditional latent variable in the inference network is regularized by the latent variable in the reconstruction network to facilitate information flow between the conditional latent variable and novel views. We also propose a statistic distance measurement dubbed the mean local maximum mean discrepancy (MLMMD) to enable the measurement of the statistic distance between two distributions with high-resolution latent variables, which can capture richer information than their low-resolution counterparts. Finally, we propose a viewpoint-dependent indirect view synthesis method to synthesize novel views more efficiently by leveraging adaptive convolution. Experimental results show that our proposed methods outperform state-of-the-art methods on different light field datasets.

Item ID: 76023
Item Type: Article (Research - C1)
ISSN: 1941-0042
Keywords: Image reconstruction, Convolution, Superresolution, Spatial resolution, Feature extraction, Cameras, Training, Light field image reconstruction, variational autoencoder, statistic distance measurement, indirect view synthesis, adaptive convolut
Copyright Information: © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Funders: Australian Research Council (ARC)
Projects and Grants: ARC Discovery Projects Funding Scheme (Grant Number: DP220101634)
Date Deposited: 14 Sep 2022 08:42
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4603 Computer vision and multimedia computation > 460303 Computational imaging @ 60%
46 INFORMATION AND COMPUTING SCIENCES > 4603 Computer vision and multimedia computation > 460304 Computer vision @ 40%
SEO Codes: 22 INFORMATION AND COMMUNICATION SERVICES > 2205 Media services > 220501 Animation, video games and computer generated imagery services @ 50%
22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220406 Graphics @ 50%
Downloads: Total: 1
Last 12 Months: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page