Abstract
Homography estimation is a basic computer vision task, which aims to obtain the transformation from multi-view images for image alignment. Unsupervised learning homography estimation trains a convolution neural network for feature extraction and transformation matrix regression. While the state-of-the-art homography method is based on convolution neural networks, few work focuses on transformer which shows superiority in high-level vision tasks. In this paper, we propose a strong-baseline model based on the Swin Transformer, which combines convolution neural network for local features and transformer module for global features. Moreover, a cross non-local layer is introduced to search the matched features within the feature maps this http URL the homography regression stage, we adopts an attention layer for the channels of correlation volume, which can drop out some weak correlation feature points. The experiment shows that in 8 Degree-of-Freedoms(DOFs) homography estimation our methods overperform the state-of-the-art method.
Abstract (translated)
URL
https://arxiv.org/abs/2212.03029