MAD-DR: mAP Compression for Visual Localization with Matchness Aware Descriptor Dimension Reduction
Abstract
3D-structure based methods remain the top-performing solution for long-term visual localization tasks. However, the dimension of existing local descriptors is usually high and the map takes huge storage space, especially for large-scale scenes. We propose an asymmetric framework which learns to reduce the dimension of local descriptors and match them jointly. We can compress existing local descriptor to 1/256 of original size while maintaining high matching performance. Experiments on public visual localization datasets show that our pipeline obtains better results than existing map compression methods and non-structure based alternatives.
Cite
Text
Wang. "MAD-DR: mAP Compression for Visual Localization with Matchness Aware Descriptor Dimension Reduction." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72784-9_15Markdown
[Wang. "MAD-DR: mAP Compression for Visual Localization with Matchness Aware Descriptor Dimension Reduction." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/wang2024eccv-maddr/) doi:10.1007/978-3-031-72784-9_15BibTeX
@inproceedings{wang2024eccv-maddr,
title = {{MAD-DR: mAP Compression for Visual Localization with Matchness Aware Descriptor Dimension Reduction}},
author = {Wang, Qiang},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72784-9_15},
url = {https://mlanthology.org/eccv/2024/wang2024eccv-maddr/}
}