Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from keypoint correspondences established between monocular 2D images. Current NRSfM methods lack statistical robustness, which is the ability to cope with correspondence errors. T ...
This paper proposes a representational model for image pairs such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The model couples the ...
Current research of designing prosthetic robotic hands mainly focuses on improving their functionality by devising new mechanical structures and actuation systems. Most of existing work relies on a single structure/system (e.g., bone-only or tissue-only) a ...
We present an image-based pipeline for generating geometrical digital twins (GDTs) of stone masonry elements with detail down to the stone level. For this purpose, we acquire RGB images of the individual stones and of the wall during the construction phase ...
In this thesis, we advocate that Computer-Aided Engineering could benefit from a Geometric Deep Learning revolution,
similarly to the way that Deep Learning revolutionized Computer Vision.
To do so, we consider a variety of Computer-Aided Engineering pr ...
The field of artificial intelligence is set to fuel the future of mobility by driving forward the transition from advanced driver-assist systems to fully autonomous vehicles (AV). Yet the current technology, backed by cutting-edge deep learning techniques, ...
In this work we perform a neutron Bragg edge tomography of stainless steel 316L additive manufacturing samples, one as built via standard laser powder bed fusion, and one using the novel three-dimensional (3D) laser shock peening technique. First, we consi ...
Medical interventions in the central nervous system (CNS) are challenging due to the complexity and delicacy of the brain tissue. Techniques that do not require opening the skull would alleviate patient discomfort and increase post-operative outputs. Vesse ...
Self-organization is the spontaneous formation of ordered patterns and networks from a population of comparatively simple elements or individuals with no prior information on neither the formation process nor the final organization. While the construction ...
There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an approach to volume ...
Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...
