Dense Depth Estimation from Multiple 360-degree Images Using Virtual Depth

TL;DR

This paper introduces a novel dense depth estimation pipeline for multiview 360-degree images that uses a spherical camera model with virtual depth to improve accuracy, validated on natural and synthetic datasets.

Contribution

It extends spherical camera models to multiview with translation scaling and proposes a virtual depth-based dense depth estimation method.

Findings

Improved depth estimation accuracy over state-of-the-art methods.

Effective compensation for radial distortion in 360-degree images.

Validated on both natural and synthetic datasets.

Abstract

In this paper, we propose a dense depth estimation pipeline for multiview 360{\deg} images. The proposed pipeline leverages a spherical camera model that compensates for radial distortion in 360{\deg} images. The key contribution of this paper is the extension of a spherical camera model to multiview by introducing a translation scaling scheme. Moreover, we propose an effective dense depth estimation method by setting virtual depth and minimizing photonic reprojection error. We validate the performance of the proposed pipeline using the images of natural scenes as well as the synthesized dataset for quantitive evaluation. The experimental results verify that the proposed pipeline improves estimation accuracy compared to the current state-of-art dense depth estimation methods.