Image Quality, Uniformity and Computation Improvement of Compressive Light Field Displays with U-Net

TL;DR

This paper introduces a U-Net based approach for compressive light field synthesis that outperforms existing methods in image quality, uniformity, and computational efficiency.

Contribution

It presents a novel application of U-Net for light field synthesis, improving upon prior CNN and iterative algorithms.

Findings

Enhanced image quality and uniformity in light field synthesis.

Reduced computational requirements compared to previous methods.

Demonstrated superiority over stacked CNN and iterative algorithms.

Abstract

We apply the U-Net model for compressive light field synthesis. Compared to methods based on stacked CNN and iterative algorithms, this method offers better image quality, uniformity and less computation.