DfHM: A Hierarchical Approach for Matching Pairs of Images Using Graph Attention Neural Networks

We introduce a cutting-edge approach for matching a pair of images by using a multi-dimension graph which is constructed from the images and processed using graph attention neural networks. Our method is detector-free, and in contrast to the state-of-the-art, it uses the hierarchical mechanism, a novel approach to establish image correspondence. Our framework consists of three key components: 1) a convolution neural network to compute the embedding of the hierarchical grid cell of the image, 2) a graph attention neural network that establishes correspondences between regions at each hierarchical level, and 3) a neural network model used to establish pixel-level correspondence. All three components are trained jointly to ensure optimal performance. By using the hierarchical mechanism, our model is shown to be competitive with the state-of-the-art methods and even provides performance overhead on various datasets using similar relevant metrics.