RF-Net: An End-to-End Image Matching Network Based on Receptive Field
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.
Cite
Text
Shen et al. "RF-Net: An End-to-End Image Matching Network Based on Receptive Field." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00832Markdown
[Shen et al. "RF-Net: An End-to-End Image Matching Network Based on Receptive Field." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/shen2019cvpr-rfnet/) doi:10.1109/CVPR.2019.00832BibTeX
@inproceedings{shen2019cvpr-rfnet,
title = {{RF-Net: An End-to-End Image Matching Network Based on Receptive Field}},
author = {Shen, Xuelun and Wang, Cheng and Li, Xin and Yu, Zenglei and Li, Jonathan and Wen, Chenglu and Cheng, Ming and He, Zijian},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00832},
url = {https://mlanthology.org/cvpr/2019/shen2019cvpr-rfnet/}
}