High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction release_4hhflpwqfrattlw7iglhapbl5q

by Nan Meng, Hayden K.-H. So, Xing Sun, Edmund Y. Lam

Released as a article .

2019  

Abstract

We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and angular details separately. Such methods have difficulties with non-Lambertian surfaces or occlusions. In contrast, we formulate light field super-resolution (LFSR) as tensor restoration and develop a learning framework based on a two-stage restoration with 4-dimensional (4D) convolution. This allows our model to learn the features capturing the geometry information encoded in multiple adjacent views. Such geometric features vary near the occlusion regions and indicate the foreground object border. To train a feasible network, we propose a novel normalization operation based on a group of views in the feature maps, design a stage-wise loss function, and develop the multi-range training strategy to further improve the performance. Evaluations are conducted on a number of light field datasets including real-world scenes, synthetic data, and microscope light fields. The proposed method achieves superior performance and less execution time comparing with other state-of-the-art schemes.
In text/plain format

Archived Files and Locations

application/pdf  4.4 MB
file_g4rhwfaounekvkbdnqderpmywe
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   accepted
Date   2019-11-21
Version   v3
Language   en ?
arXiv  1910.01426v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2dfa188b-4887-4361-be6f-2351ca8b1659
API URL: JSON