This paper reviews recent deep learning-based registration methods. Registration is the process that computes the transformation that aligns datasets, and the accuracy of the result depends on multiple factors. The most significant factors are the size 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 defined by multiple parameters, such as non-rigid deformations. Deep Registration Networks (DRNs) are those architectures trying to solve the alignment task using a learning algorithm. In this review, we classify these methods according to a proposed framework based on the traditional registration pipeline. This pipeline consists of four steps: target selection, feature extraction, feature matching, and transform computation for the alignment. This new paradigm introduces a higher-level understanding of registration, which makes explicit the challenging problems of traditional approaches. The main contribution of this work is to provide a comprehensive starting point to address registration problems from a learning-based perspective and to understand the new range of possibilities.

RGB-D (Red Green Blue and Depth) sensors are devices that can provide color and depth information from a scene at the same time. Recently, they have been widely used in many solutions due to their commercial growth from the entertainment market to many diverse areas (e.g., robotics, CAD, etc.). In the research community, these devices have had good uptake due to their acceptable levelofaccuracyformanyapplicationsandtheirlowcost,butinsomecases,theyworkatthelimitof their sensitivity, near to the minimum feature size that can be perceived. For this reason, calibration processes are critical in order to increase their accuracy and enable them to meet the requirements of such kinds of applications. To the best of our knowledge, there is not a comparative study of calibration algorithms evaluating its results in multiple RGB-D sensors. Specifically, in this paper, a comparison of the three most used calibration methods have been applied to three different RGB-D sensors based on structured light and time-of-flight. The comparison of methods has been carried out by a set of experiments to evaluate the accuracy of depth measurements. Additionally, an object reconstruction application has been used as example of an application for which the sensor works at the limit of its sensitivity. The obtained results of reconstruction have been evaluated through visual inspection and quantitative measurements.

Tractography from diffusion MRI enables the mapping of white matter pathways. A key challenge is the automatic segmentation of streamlines into anatomically meaningful bundles, which is strongly affected by class imbalance: common bundles dominate the training data, whereas bundles such as the fornix are severely underrepresented (<0.2% of streamlines). This work proposes a tractography segmentation framework that combines a generative oversampling strategy based on Variational Autoencoders (VAEs) with a streamline-wise convolutional classifier operating on FiberMap representations. The generative model is applied in a targeted manner only to underrepresented bundles, and its effect is compared with two alternative oversampling schemes: simple sample duplication and the Synthetic Minority Oversampling Technique (SMOTE). Experiments on the Tractoinferno dataset, comprising 32 white matter bundles, show that all configurations yield similar global performance, with macro F1-scores around 90–91%. In contrast, performance on underrepresented bundles changes markedly, with VAE-based oversampling improving left/right fornix F1-scores from 77.2%/68.7% to 90.4%/92.5%, yielding an average gain of 18.5 percentage points across the two fornix bundles. Sample duplication increases recall but substantially reduces precision, while SMOTE achieves the highest recall at the cost of more false positives. A complementary three-dimensional geometric analysis revealed a fidelity–coverage trade-off, with SMOTE more closely reproducing real length and curvature distributions while VAE samples provided greater coverage of real trajectories. Overall, the VAE achieved the most favorable precision–recall balance for the targeted fornix bundles. These results suggest that targeted VAE-based oversampling is a practical strategy for mitigating extreme imbalance in tractography segmentation, improving the recognition of underrepresented bundles without materially affecting performance on dominant bundles.