High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registration

TL;DR

This paper introduces a fast, high-resolution panoramic depth estimation method that improves accuracy and efficiency over existing approaches by using a novel registration technique with a real-time panoramic depth map as a reference.

Contribution

The authors propose a new registration approach for high-resolution panoramic depth estimation that simplifies stitching and enhances accuracy compared to prior methods like 360MonoDepth.

Findings

Produces higher resolution depth maps (2048x1024) than previous methods.

Achieves faster computation times while maintaining or improving quality.

Outperforms existing methods on unseen datasets.

Abstract

We propose a novel approach to compute high-resolution (2048x1024 and higher) depths for panoramas that is significantly faster and qualitatively and qualitatively more accurate than the current state-of-the-art method (360MonoDepth). As traditional neural network-based methods have limitations in the output image sizes (up to 1024x512) due to GPU memory constraints, both 360MonoDepth and our method rely on stitching multiple perspective disparity or depth images to come out a unified panoramic depth map. However, to achieve globally consistent stitching, 360MonoDepth relied on solving extensive disparity map alignment and Poisson-based blending problems, leading to high computation time. Instead, we propose to use an existing panoramic depth map (computed in real-time by any panorama-based method) as the common target for the individual perspective depth maps to register to. This key idea made producing globally consistent stitching results from a straightforward task. Our experiments show that our method generates qualitatively better results than existing panorama-based methods, and further outperforms them quantitatively on datasets unseen by these methods.