2020/03/19 by Yuan Gao, Gao, Yuan, Robert Bregovic +6
Computer Science · Engineering · Physics and Astronomy · #Advanced Optical Sensing Technologies #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Multimedia (cs.MM) #Optical measurement and interference techniques #cs.CV #cs.MM #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2003.08865
arxiv created 2020/03/19 · openalex publication_date 2020/03/19 · arxiv updated 2020/03/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The Image-Based Rendering (IBR) approach using Shearlet Transform (ST) is one of the most effective methods for Densely-Sampled Light Field (DSLF) reconstruction. The ST-based DSLF reconstruction typically relies on an iterative thresholding algorithm for Epipolar-Plane Image (EPI) sparse regularization in shearlet domain, involving dozens of transformations between image domain and shearlet domain, which are in general time-consuming. To overcome this limitation, a novel learning-based ST approach, referred to as Deep Residual Shearlet Transform (DRST), is proposed in this paper. Specifically, for an input sparsely-sampled EPI, DRST employs a deep fully Convolutional Neural Network (CNN) to predict the residuals of the shearlet coefficients in shearlet domain in order to reconstruct a densely-sampled EPI in image domain. The DRST network is trained on synthetic Sparsely-Sampled Light Field (SSLF) data only by leveraging elaborately-designed masks. Experimental results on three challenging real-world light field evaluation datasets with varying moderate disparity ranges (8 - 16 pixels) demonstrate the superiority of the proposed learning-based DRST approach over the non-learning-based ST method for DSLF reconstruction. Moreover, DRST provides a 2.4x speedup over ST, at least.