You can find details on the benchmark and evaluation in: Visual Localization using Imperfect 3D Models from the Internet

If you use the benchmark, please cite the publication:

@article{Panek2023cadloc,
title={{Visual Localization using Imperfect 3D Models from the Internet}},
author={Vojtech Panek and Zuzana Kukelova and Torsten Sattler},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
year={2023}}

Scripts

Evaluation script
Rendering script

If you find a mistake or have a question to the benchmark, please let us know by opening an issue in the repository.

Visual Localization on Imperfect 3D Mesh Models from the Internet

Scripts