Check out WayveScenes101 - a publicly available dataset from Wayve, an autonomous driving company, meant to serve as a benchmark for novel view synthesis models for driving applications.
The Dataset is a collection of high-resolution images and camera poses designed to advance research in novel view synthesis and scene reconstruction for autonomous driving applications.
WayveScenes101 has 101 scenes from diverse driving environments, including urban, suburban, and highway environments, recorded in the US and UK across different weather and lighting conditions.
5 time-synchronized cameras: front-forward, left-forward, right-forward, left-backward, right-backward
The high frame rate of 10 frames per second for each camera means more accurate scene reconstruction, especially for dynamic scenes.
The Dataset captures various conditions, such as weather, road types, times of day, dynamic agents, and illumination changes.
When you download the Dataset, it's actually 101,000 total images (101 scenes x 5 cameras x 20 seconds x 10 frames per second)
This unique Dataset of multi-view driving scenes is an absolute must if you're training or evaluating novel view synthesis models on realistic automotive data.
Top comments (0)