You are holding in your hands… oh, come on, who holds books like this in their hands
anymore? Anyway, you are reading this, and it means that I have managed to release one of …

Using synthetic data for training deep neural networks for robotic manipulation holds the
promise of an almost unlimited amount of pre-labeled training data, generated safely out of …

While deep learning has recently achieved great success on multi-view stereo (MVS),
limited training data makes the trained model hard to be generalized to unseen scenarios …

We present a system for training deep neural networks for object detection using synthetic
images. To handle the variability in real-world data, the system relies upon the technique of …

The success of deep learning in computer vision is based on the availability of large
annotated datasets. To lower the need for hand labeled images, virtually rendered 3D …

Datasets have gained an enormous amount of popularity in the computer vision community,
from training and evaluation of Deep Learning-based methods to benchmarking …

In human learning, it is common to use multiple sources of information jointly. However, most
existing feature learning approaches learn from only a single task. In this paper, we propose …

We present structured domain randomization (SDR), a variant of domain randomization
(DR) that takes into account the structure of the scene in order to add context to the …

UnrealCV is a project to help computer vision researchers build virtual worlds using Unreal
Engine 4 (UE4). It extends UE4 with a plugin by providing (1) A set of UnrealCV commands …

The finding that very large networks can be trained efficiently and reliably has led to a
paradigm shift in computer vision from engineered solutions to learning formulations. As a …