ContextDesc: Local Descriptor Augmentation With Cross-Modality Context

Zixin Luo, Tianwei Shen, Lei Zhou, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2527-2536

Abstract


Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations. In this paper, we go beyond the local detail representation by introducing context awareness to augment off-the-shelf local feature descriptors. Specifically, we propose a unified learning framework that leverages and aggregates the cross-modality contextual information, including (i) visual context from high-level image representation, and (ii) geometric context from 2D keypoint distribution. Moreover, we propose an effective N-pair loss that eschews the empirical hyper-parameter search and improves the convergence. The proposed augmentation scheme is lightweight compared with the raw local feature description, meanwhile improves remarkably on several large-scale benchmarks with diversified scenes, which demonstrates both strong practicality and generalization ability in geometric matching applications.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Luo_2019_CVPR,
author = {Luo, Zixin and Shen, Tianwei and Zhou, Lei and Zhang, Jiahui and Yao, Yao and Li, Shiwei and Fang, Tian and Quan, Long},
title = {ContextDesc: Local Descriptor Augmentation With Cross-Modality Context},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}