Wide neural networks are biased towards learning certain functions,
infl...
This paper proposes a generalizable, end-to-end deep learning-based meth...
Over-parameterized residual networks (ResNets) are amongst the most
succ...
We study the properties of various over-parametrized convolutional neura...
Existing deep methods produce highly accurate 3D reconstructions in ster...
Deep residual network architectures have been shown to achieve superior
...
Early detection of COVID-19 is key in containing the pandemic. Disease
d...
Recent theoretical work has shown that massively overparameterized neura...
Efficient numerical solvers for sparse linear systems are crucial in sci...
Recent works have partly attributed the generalization ability of
over-p...
Global methods to Structure from Motion have gained popularity in recent...
Essential matrix averaging, i.e., the task of recovering camera location...
Constructing fast numerical solvers for partial differential equations (...
Incremental (online) structure from motion pipelines seek to recover the...
This paper addresses the problem of recovering projective camera matrice...
A fundamental question for edge detection in noisy images is how faint c...
Accurate estimation of camera matrices is an important step in structure...
Finding correspondences in wide baseline setups is a challenging problem...
Current state-of-the-art discrete optimization methods struggle behind w...
Discrete energy minimization is a ubiquitous task in computer vision, ye...
Clustering is a fundamental task in unsupervised learning. The focus of ...