论文标题
ABHE：所有基于注意力的同型估计
AbHE: All Attention-based Homography Estimation
论文作者
论文摘要
同型估计是一项基本的计算机视觉任务，旨在从多视图图像中获得用于图像对齐的多视图。无监督的学习同型估计估计训练一个卷积神经网络，用于提取和转换矩阵回归。虽然最先进的同型同构方法基于卷积神经网络，但很少有工作重点放在变压器上，该变压器在高级视力任务中表现出优势。在本文中，我们提出了一个基于Swin Transformer的强基线模型，该模型结合了局部特征的卷积神经网络和全局特征变压器模块。此外，引入了交叉非本地层，以搜索特征图内的匹配特征。在同型回归阶段，我们对相关量通道的注意力层采用了一个注意力层，这可能会删除一些弱相关特征点。该实验表明，在8个自由运动（DOFS）同谱估计中，我们的方法表现过最先进的方法。
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-theart homography method is based on convolution neural networks, few work focuses on transformer which shows superiority in highlevel 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 coarsely. In the homography regression stage, we adopt 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 method overperforms the state-of-the-art method.
