Light Field Reconstruction Using Shearlet Transform

TL;DR

This paper presents a novel light field reconstruction method using shearlet transform for high-quality image rendering from limited views, outperforming existing depth image-based techniques.

Contribution

It introduces a shearlet transform-based sparse representation approach for light field reconstruction from sparse perspective views.

Findings

High-quality light field reconstruction with large disparities.

Outperforms state-of-the-art depth image-based rendering methods.

Effective for applications requiring dense light field data.

Abstract

In this article we develop an image based rendering technique based on light field reconstruction from a limited set of perspective views acquired by cameras. Our approach utilizes sparse representation of epipolar-plane images in a directionally sensitive transform domain, obtained by an adapted discrete shearlet transform. The used iterative thresholding algorithm provides high-quality reconstruction results for relatively big disparities between neighboring views. The generated densely sampled light field of a given 3D scene is thus suitable for all applications which requires light field reconstruction. The proposed algorithm is compared favorably against state of the art depth image based rendering techniques.