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

Maurice Fallon (University of Oxford) · Zirui Wang (University of Illinois at Urbana Champaign) · Wenjing Bian (University of Oxford) · Xinghui Li (University of Oxford) · Yifu Tao (University of Oxford) · Jianeng Wang (University of Oxford) · Victor Prisacariu (University of Oxford)

3d point clouds6dof motionbenchmark evaluation camera posesdiverse environmentsegocentric 3d visionegocentric datasetground-truth 3d geometrylighting variationmeta aria glassesmulti-session slamnovel view synthesisrealistic environmentstrajectory recordingvisual relocalisation

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 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. Project page: https://oxdan.active.vision/