RF-Net: An End-To-End Image Matching Network Based on Receptive Field

Xuelun Shen, Cheng Wang, Xin Li, Zenglei Yu, Jonathan Li, Chenglu Wen, Ming Cheng, Zijian He; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8132-8140

Abstract


This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images. Building end-to-end trainable matching framework is desirable and challenging. The very recent approach, LF-Net, successfully embeds the entire feature extraction pipeline into a jointly trainable pipeline, and produces the state-of-the-art matching results. This paper introduces two modifications to the structure of LF-Net. First, we propose to construct receptive feature maps, which lead to more effective keypoint detection. Second, we introduce a general loss function term, neighbor mask, to facilitate training patch selection. This results in improved stability in descriptor training. We trained RF-Net on the open dataset HPatches, and compared it with other methods on multiple benchmark datasets. Experiments show that RF-Net outperforms existing state-of-the-art methods.

Related Material


[pdf]
[bibtex]
@InProceedings{Shen_2019_CVPR,
author = {Shen, Xuelun and Wang, Cheng and Li, Xin and Yu, Zenglei and Li, Jonathan and Wen, Chenglu and Cheng, Ming and He, Zijian},
title = {RF-Net: An End-To-End Image Matching Network Based on Receptive Field},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}