This paper concerns the undetermined problem of estimating geometric transformation between image pairs. Recent methods introduce deep neural networks to predict the controlling parameters of hand-crafted geometric transformation models (e.g.

The paper presents a neural network model for image registration, which generates an arbitrary displacement field to transform the input image in a way that matches the target. This neural network has several components, including a common feature extraction model that results in a 4D tensor with the correlations of local features from both images. The tensor is then transformed into a vector representation of the transformation, and later used to reconstruct a displacement field. COMMENTS Overall, the work is relatively well presented and provides details to understand most of the formulation and solution. However, there are some confusing aspects that could be clarified or stated more prominently.

This submission received mixed ratings. The most positive reviewers has a non confident rating. R1 and R2 appreciate that the paper is well written and presents an interesting approach to image registration. R1 and R3 point out that the central contribution is not clearly stated in the text. Also overlap of text in sections 3.1-3.3

This paper concerns the undetermined problem of estimating geometric transformation between image pairs. Recent methods introduce deep neural networks to predict the controlling parameters of hand-crafted geometric transformation models (e.g. However, the low-dimension parametric models are incapable of estimating a highly complex geometric transform with limited flexibility to model the actual geometric deformation from image pairs. To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment. Arbicon-Net is generalized from training data to predict the desired arbitrary continuous geometric transformation in a data-driven manner for unseen new pair of images.

This paper concerns the undetermined problem of estimating geometric transformation between image pairs. Recent methods introduce deep neural networks to predict the controlling parameters of hand-crafted geometric transformation models (e.g. However, the low-dimension parametric models are incapable of estimating a highly complex geometric transform with limited flexibility to model the actual geometric deformation from image pairs. To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment. Arbicon-Net is generalized from training data to predict the desired arbitrary continuous geometric transformation in a data-driven manner for unseen new pair of images.