Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Zirui, Bian, Wenjing, Li, Xinghui, Tao, Yifu, Wang, Jianeng, Fallon, Maurice, Prisacariu, Victor Adrian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915325312761856
author Wang, Zirui
Bian, Wenjing
Li, Xinghui
Tao, Yifu
Wang, Jianeng
Fallon, Maurice
Prisacariu, Victor Adrian
author_facet Wang, Zirui
Bian, Wenjing
Li, Xinghui
Tao, Yifu
Wang, Jianeng
Fallon, Maurice
Prisacariu, Victor Adrian
contents We introduce Oxford Day-and-Night, a large-scale, egocentric dataset for novel view synthesis (NVS) and visual relocalisation under challenging lighting conditions. Existing datasets often lack crucial combinations of features such as ground-truth 3D geometry, wide-ranging lighting variation, and full 6DoF motion. Oxford Day-and-Night addresses these gaps by leveraging Meta ARIA glasses to capture egocentric video and applying multi-session SLAM to estimate camera poses, reconstruct 3D point clouds, and align sequences captured under varying lighting conditions, including both day and night. The dataset spans over 30 $\mathrm{km}$ of recorded trajectories and covers an area of 40,000 $\mathrm{m}^2$, offering a rich foundation for egocentric 3D vision research. It supports two core benchmarks, NVS and relocalisation, providing a unique platform for evaluating models in realistic and diverse environments.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04224
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
Wang, Zirui
Bian, Wenjing
Li, Xinghui
Tao, Yifu
Wang, Jianeng
Fallon, Maurice
Prisacariu, Victor Adrian
Computer Vision and Pattern Recognition
We introduce Oxford Day-and-Night, a large-scale, egocentric dataset for novel view synthesis (NVS) and visual relocalisation under challenging lighting conditions. Existing datasets often lack crucial combinations of features such as ground-truth 3D geometry, wide-ranging lighting variation, and full 6DoF motion. Oxford Day-and-Night addresses these gaps by leveraging Meta ARIA glasses to capture egocentric video and applying multi-session SLAM to estimate camera poses, reconstruct 3D point clouds, and align sequences captured under varying lighting conditions, including both day and night. The dataset spans over 30 $\mathrm{km}$ of recorded trajectories and covers an area of 40,000 $\mathrm{m}^2$, offering a rich foundation for egocentric 3D vision research. It supports two core benchmarks, NVS and relocalisation, providing a unique platform for evaluating models in realistic and diverse environments.
title Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.04224