In this article, we provide a detailed survey of 3D Morphable Face Models over the 20 years
since they were first proposed. The challenges in building and applying these models …

Abstract 3D face reconstruction from a single image is challenging due to its ill-posed
nature. Model-based face autoencoders address this issue effectively by fitting a face model …

For many applications it is critical to know the uncertainty of a neural network's predictions.
While a variety of neural network parameter estimation methods have been proposed for …

In this work, we aim to enhance model-based face reconstruction by avoiding fitting the
model to outliers, ie regions that cannot be well-expressed by the model such as occluders …

Reconstructing two-hand interactions from a single image is a challenging problem due to
ambiguities that stem from projective geometry and heavy occlusions. Existing methods are …

Uncertainty quantification of machine learning and deep learning methods plays an
important role in enhancing trust to the obtained result. In recent years, a numerous number …

We propose to view non-rigid surface registration as a probabilistic inference problem.
Given a target surface, we estimate the posterior distribution of surface registrations. We …

Uncertainty quantification of machine learning and deep learning methods plays an
important role in enhancing trust to the obtained result. In recent years, a numerous number …

We frequently encounter the need to reconstruct the full 3D surface from a given part of a
bone in areas such as orthopaedics and surgical planning. Once we establish …

Deep latent variable models introduce a new class of generative models which are able to
handle unstructured data and encode non-linear dependencies. Despite their known …