CVPR2025

RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges

Thibaut Loiseau, Guillaume Bourmaud

Abstract

Figure 1 . We introduce RUBIKa benchmark based on the images from nuScenes for fine grain evaluation of camera pose estimation methods. RUBIK is made of image pairs spanning three difficulty criteria, in terms of scene overlap, scale ratio, and difference of viewpoint angles. It contains 16.5K image pairs across 33 difficulty levels. We use it to provide a comprehensive benchmarking of 14 methods.