Arbitrary Volumetric Refocusing of Dense and Sparse Light Fields

TL;DR

This paper introduces an end-to-end deep learning pipeline for arbitrary volumetric refocusing of dense and sparse light fields, overcoming previous limitations to generate multiple in-focus and out-of-focus regions simultaneously.

Contribution

It presents a novel pixel-dependent shift-and-sum refocusing method combined with a U-Net based model to eliminate ghosting artifacts in sparse light fields.

Findings

Sparse LFs refocused achieve SSIM > 0.9 with only 20% data

Method effectively refocuses multiple regions simultaneously

Deep learning reduces ghosting artifacts significantly

Abstract

A four-dimensional light field (LF) captures both textural and geometrical information of a scene in contrast to a two-dimensional image that captures only the textural information of a scene. Post-capture refocusing is an exciting application of LFs enabled by the geometric information captured. Previously proposed LF refocusing methods are mostly limited to the refocusing of single planar or volumetric region of a scene corresponding to a depth range and cannot simultaneously generate in-focus and out-of-focus regions having the same depth range. In this paper, we propose an end-to-end pipeline to simultaneously refocus multiple arbitrary planar or volumetric regions of a dense or a sparse LF. We employ pixel-dependent shifts with the typical shift-and-sum method to refocus an LF. The pixel-dependent shifts enables to refocus each pixel of an LF independently. For sparse LFs, the shift-and-sum method introduces ghosting artifacts due to the spatial undersampling. We employ a deep learning model based on U-Net architecture to almost completely eliminate the ghosting artifacts. The experimental results obtained with several LF datasets confirm the effectiveness of the proposed method. In particular, sparse LFs refocused with the proposed method archive structural similarity index higher than 0.9 despite having only 20% of data compared to dense LFs.