Depth Estimation Through a Generative Model of Light Field Synthesis

TL;DR

This paper introduces a generative model-based framework for high-quality continuous depth map recovery from light field data, integrating advanced regularization techniques for improved accuracy.

Contribution

It presents a novel generative model of light fields parametrized by depth, enabling accurate depth estimation with regularization techniques.

Findings

High-quality depth maps can be recovered from light field data.

The generative model effectively incorporates regularization for improved accuracy.

The framework advances depth estimation techniques in light field photography.

Abstract

Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation.