When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)

Abstract

Registration is the process that computes the transformation that aligns sets of data. Commonly, a registration process can be divided into four main steps: target selection, feature extraction, feature matching, and transform computation for the alignment. The accuracy of the result depends on multiple factors, the most significant are the quantity of input data, the presence of noise, outliers and occlusions, the quality of the extracted features, real-time requirements and the type of transformation, especially those ones defined by multiple parameters, like non-rigid deformations.Recent advancements in machine learning could be a turning point in these issues, particularly with the development of deep learning (DL) techniques, which are helping to improve multiple computer vision problems through an abstract understanding of the input data. In this paper, a review of deep learning-based registration methods is presented. We classify the different papers proposing a framework extracted from the traditional registration pipeline to analyse the new learning-based proposal strengths. Deep Registration Networks (DRNs) try to solve the alignment task either replacing part of the traditional pipeline with a network or fully solving the registration problem. The main conclusions extracted are, on the one hand, 1) learning-based registration techniques cannot always be clearly classified in the traditional pipeline. 2) These approaches allow more complex inputs like conceptual models as well as the traditional 3D datasets. 3) In spite of the generality of learning, the current proposals are still ad hoc solutions. Finally, 4) this is a young topic that still requires a large effort to reach general solutions able to cope with the problems that affect traditional approaches.

A Review on Deep Learning Techniques for Video Prediction

“…2 values estimated based on the framerate and the total number of frames or videos, as the original values are not provided by the authors. 3 custom indicates that as many frames as needed can be generated. This is related to datasets generated from a game, algorithm or simulation, involving interaction or randomness.…”

“…Even so, video prediction models are able to extract rich spatio-temporal features from natural videos in a self-supervised fashion. This was fostered by the great strides deep learning has made in different research fields such as human action recognition and prediction [1], semantic segmentation [2], and registration [3], to name a few. Because of their ability to learn adequate representations from high-dimensional data [4], deep learning-Fig.…”

Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes

“…Aligning data to a consistent frame of reference is a crucial preprocessing step for many applications [44]. When the correspondences between two shapes are available, the rigid transformation relating them can be analytically computed [5].…”