360 in the Wild: Dataset for Depth Prediction and View Synthesis

TL;DR

This paper introduces a large-scale, real-world 360-degree video dataset with pose and depth annotations, aimed at advancing depth prediction and view synthesis in diverse environments.

Contribution

It provides the first extensive real-world 360° dataset with pose and depth, enabling improved learning for depth estimation and view synthesis tasks.

Findings

Dataset contains 25,000 images with pose and depth info.

Demonstrates dataset's utility for depth estimation and view synthesis.

Includes diverse indoor and outdoor scenes.

Abstract

The large abundance of perspective camera datasets facilitated the emergence of novel learning-based strategies for various tasks, such as camera localization, single image depth estimation, or view synthesis. However, panoramic or omnidirectional image datasets, including essential information, such as pose and depth, are mostly made with synthetic scenes. In this work, we introduce a large scale 360$^{\circ}$ videos dataset in the wild. This dataset has been carefully scraped from the Internet and has been captured from various locations worldwide. Hence, this dataset exhibits very diversified environments (e.g., indoor and outdoor) and contexts (e.g., with and without moving objects). Each of the 25K images constituting our dataset is provided with its respective camera's pose and depth map. We illustrate the relevance of our dataset for two main tasks, namely, single image depth estimation and view synthesis.