Total Variation-Based Dense Depth from Multi-Camera Array

TL;DR

This paper introduces a new, computationally efficient framework for dense depth estimation from multi-camera arrays using local EPI analysis and Total Variation minimization, achieving high accuracy with lower computational costs.

Contribution

The paper presents a novel depth estimation framework combining local EPI analysis and TV minimization, reducing computational requirements while maintaining accuracy.

Findings

Performs well compared to top methods in accuracy.

Significantly reduces computational costs.

Effective on diverse scene types.

Abstract

Multi-Camera arrays are increasingly employed in both consumer and industrial applications, and various passive techniques are documented to estimate depth from such camera arrays. Current depth estimation methods provide useful estimations of depth in an imaged scene but are often impractical due to significant computational requirements. This paper presents a novel framework that generates a high-quality continuous depth map from multi-camera array/light field cameras. The proposed framework utilizes analysis of the local Epipolar Plane Image (EPI) to initiate the depth estimation process. The estimated depth map is then processed using Total Variation (TV) minimization based on the Fenchel-Rockafellar duality. Evaluation of this method based on a well-known benchmark indicates that the proposed framework performs well in terms of accuracy when compared to the top-ranked depth estimation methods and a baseline algorithm. The test dataset includes both photorealistic and non-photorealistic scenes. Notably, the computational requirements required to achieve an equivalent accuracy are significantly reduced when compared to the top algorithms. As a consequence, the proposed framework is suitable for deployment in consumer and industrial applications.