Deep Decoding of $\ell_\infty$-coded Light Field Images

TL;DR

This paper introduces a low-complexity light field image compression system using an $ ext{l}_ ext{infty}$-constrained approach with a CNN decoder, achieving high-fidelity reconstruction and outperforming existing methods.

Contribution

It proposes a novel $ ext{l}_ extinfty$-constrained compression system with a simple DPCM encoder and a CNN decoder tailored for light field images, emphasizing high-quality reconstruction.

Findings

CNN decoder significantly reduces compression artifacts.

Outperforms state-of-the-art $ ext{l}_ extinfty$-based methods.

Low-complexity encoding suitable for inexpensive cameras.

Abstract

To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations. The added capability and flexibility are gained at the cost of gathering typically more than $100\times$ greater amount of information than conventional images. To cope with this issue, several light field compression schemes have been introduced. However, their ways of exploiting correlations of multidimensional light field data are complex and are hence not suited for inexpensive light field cameras. In this work, we propose a novel $\ell_\infty$-constrained light-field image compression system that has a very low-complexity DPCM encoder and a CNN-based deep decoder. Targeting high-fidelity reconstruction, the CNN decoder capitalizes on the $\ell_\infty$-constraint and light field properties to remove the compression artifacts and achieves significantly better performance than existing state-of-the-art $\ell_2$-based light field compression methods.