Saved in:
Bibliographic Details
Main Authors: Park, Kibaek, Rameau, Francois, Park, Jaesik, Kweon, In So
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.18898
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910514113675264
author Park, Kibaek
Rameau, Francois
Park, Jaesik
Kweon, In So
author_facet Park, Kibaek
Rameau, Francois
Park, Jaesik
Kweon, In So
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18898
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 360 in the Wild: Dataset for Depth Prediction and View Synthesis
Park, Kibaek
Rameau, Francois
Park, Jaesik
Kweon, In So
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title 360 in the Wild: Dataset for Depth Prediction and View Synthesis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.18898