RF-Net: An End-to-End Image Matching Network based on Receptive Field
This work addresses image matching for computer vision applications, but it is incremental as it modifies an existing approach (LF-Net).
The paper tackled the problem of sparse image matching by proposing RF-Net, an end-to-end trainable network based on receptive field, which outperformed existing state-of-the-art methods on benchmark datasets.
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.