WayveScenes101: A Dataset and Benchmark for Novel View Synthesis in Autonomous Driving

TL;DR

WayveScenes101 is a comprehensive dataset and benchmark designed to advance novel view synthesis in complex, dynamic driving scenes with diverse environmental conditions, occlusions, and challenging visual effects.

Contribution

The paper introduces WayveScenes101, a new dataset with diverse driving scenarios and an evaluation protocol for assessing model generalization in novel view synthesis.

Findings

Dataset includes 101 challenging driving scenes with dynamic elements.

Provides camera poses and detailed scene metadata for comprehensive benchmarking.

Establishes an evaluation protocol for off-axis view synthesis generalization.

Abstract

We present WayveScenes101, a dataset designed to help the community advance the state of the art in novel view synthesis that focuses on challenging driving scenes containing many dynamic and deformable elements with changing geometry and texture. The dataset comprises 101 driving scenes across a wide range of environmental conditions and driving scenarios. The dataset is designed for benchmarking reconstructions on in-the-wild driving scenes, with many inherent challenges for scene reconstruction methods including image glare, rapid exposure changes, and highly dynamic scenes with significant occlusion. Along with the raw images, we include COLMAP-derived camera poses in standard data formats. We propose an evaluation protocol for evaluating models on held-out camera views that are off-axis from the training views, specifically testing the generalisation capabilities of methods. Finally, we provide detailed metadata for all scenes, including weather, time of day, and traffic conditions, to allow for a detailed model performance breakdown across scene characteristics. Dataset and code are available at https://github.com/wayveai/wayve_scenes.