RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges
Thibaut Loiseau, Guillaume Bourmaud
2025Year
1Top-tier citations
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext e8002030-a3af-4c67-a338-ff53bfa9906bCited by top-tier papers1
Ask how each one uses itBuilds on21
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
- LightGlue: Local Feature Matching at Light SpeedPhilipp Lindenberger, Paul-Edouard Sarlin, Marc PollefeysICCV 2023 · 936 citations
- DISK: Learning local features with policy gradientMichal J. Tyszkiewicz, Pascal Fua, Eduard TrullsNeurIPS 2020 · 652 citations
- COTR: Correspondence Transformer for Matching Across ImagesWei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi et al.ICCV 2021 · 318 citations
- DUSt3R: Geometric 3D Vision Made EasyShuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii et al.CVPR 2024 · 302 citations
Related papers
- Princeton365: A Diverse Dataset with Accurate Camera PoseKarhan Kayan, Stamatis Alexandropoulos, Rishabh Jain, Yiming Zuo et al.ICCV 2025
- R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple CamerasAron Schmied, Tobias Fischer, Martin Danelljan, Marc Pollefeys et al.ICCV 2023 · 52 citations
- HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD MapsXuchang Zhong, Xu Cao, Jinke Feng, Hao FangCVPR 2026
- ORBIT: Benchmarking SfM in the Wild with 360° VideoSara Sabour, Richard Tucker, Marcus Brubaker, Saurabh Saxena et al.CVPR 2026
- BabelCalib: A Universal Approach to Calibrating Central CamerasYaroslava Lochman, Kostiantyn Liepieshov, Jianhui Chen, Michal Perdoch et al.ICCV 2021 · 20 citations
