Year: 2020
Type: article
Abstract: Shearlet Transform (ST) has been instrumental for the Densely-Sampled Light Field (DSLF) reconstruction, as it sparsifies the underlying Epipolar-Plane Images (EPIs). The sought sparsification is implemented through an iterative regularization, which tends to be slow because of the time spent on domain transformations for dozens of iterations. To overcome this limitation, this letter proposes a novel self-supervised DSLF reconstruction method, CycleST, which employs ST and cycle consistency. Specifically, CycleST is composed of an encoder-decoder network and a residual learning strategy that restore the shearlet coefficients of densely-sampled EPIs using EPI-reconstruction and cycle-consistency losses. CycleST is a self-supervised approach that can be trained solely on Sparsely-Sampled Light Fields (SSLFs) with small disparity ranges (≤8 pixels). Experimental results of DSLF reconstruction on SSLFs with large disparity ranges (16 - 32 pixels) demonstrate the effectiveness and efficiency of the proposed CycleST method. Furthermore, CycleST achieves ~ 9x speedup over ST, at least.
Source: IEEE Signal Processing Letters
Authors: Yuan Gao, Robert Bregovic, Atanas Gotchev
Institutions: Tampere University, University of Tampere
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Academy of Finland
Award: G5746524021
OpenAlex ID: W3041540016