Fast and Accurate Reconstruction of Compressed Color Light Field

TL;DR

This paper introduces a neural network-based method for fast, high-quality reconstruction of color light fields from a single compressed image, eliminating the need for multi-lens systems and improving efficiency over prior approaches.

Contribution

It presents a novel neural network that efficiently reconstructs high-quality color light fields from compressed images, including color channel compression, and introduces an unsupervised depth map extraction method.

Findings

Outperforms existing methods in reconstruction quality

Reduces computational complexity significantly

Eliminates the need for a color filter array in hardware

Abstract

Light field photography has been studied thoroughly in recent years. One of its drawbacks is the need for multi-lens in the imaging. To compensate that, compressed light field photography has been proposed to tackle the trade-offs between the spatial and angular resolutions. It obtains by only one lens, a compressed version of the regular multi-lens system. The acquisition system consists of a dedicated hardware followed by a decompression algorithm, which usually suffers from high computational time. In this work, we propose a computationally efficient neural network that recovers a high-quality color light field from a single coded image. Unlike previous works, we compress the color channels as well, removing the need for a CFA in the imaging system. Our approach outperforms existing solutions in terms of recovery quality and computational complexity. We propose also a neural network for depth map extraction based on the decompressed light field, which is trained in an unsupervised manner without the ground truth depth map.