Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …

To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the
map** relationship between them is one-to-many. Previous works based on the pixel-wise …

Drug toxicity prediction is an important step in ensuring patient safety during drug design
studies. While traditional preclinical studies have historically relied on animal models to …

Generative flows and diffusion models have been predominantly trained on ordinal data, for
example natural images. This paper introduces two extensions of flows and diffusion for …

We introduce a novel method using a new generative model that automatically learns
effective representations of the target and background appearance to detect, segment and …

This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although
this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty …

Abstract 3D human pose estimation from monocular images is a highly ill-posed problem
due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these …

We formulate a general framework for building structural causal models (SCMs) with deep
learning components. The proposed approach employs normalising flows and variational …

Normalizing flows have recently demonstrated promising results for low-level vision tasks.
For image super-resolution (SR), it learns to predict diverse photo-realistic high-resolution …

Existing neural network-based autonomous systems are shown to be vulnerable against
adversarial attacks, therefore sophisticated evaluation of their robustness is of great …