Nowadays, there are outstanding strides towards a future with autonomous vehicles on our
roads. While the perception of autonomous vehicles performs well under closed-set …

Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene
information from single camera images, which is trainable on arbitrary image sequences …

In this paper, we present a novel unsupervised domain adaptation (UDA) method, named
Domain Adaptive Relational Reasoning (DARR), to generalize 3D multi-organ segmentation …

State-of-the-art self-supervised learning approaches for monocular depth estimation usually
suffer from scale ambiguity. They do not generalize well when applied on distance …

Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift
between the distribution of unlabeled data from the target domain wrt labeled data from the …

Semantic segmentation is used in many fields, and most fields not only require models with
high-quality predictions but also require real-time speed in the forward inference phase …

The task of semantic segmentation requires a model to assign semantic labels to each pixel
of an image. However, the performance of such models degrades when deployed in an …

One major task in automated driving is the development of robust and safe visual perception
modules. It is of utmost importance that visual perception reacts adequately to so-called …

Scene understanding is paramount in robotics, self-navigation, augmented reality, and many
other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure …

Deep neural networks (DNNs) have proven their capabilities in the past years and play a
significant role in environment perception for the challenging application of automated …