Training data is the key ingredient for deep learning approaches, but difficult to obtain for the
specialized domains often encountered in robotics. We describe a synthesis pipeline …

BlenderProc is an open-source and modular pipeline for rendering photorealistic images of
procedurally generated 3D scenes which can be used for training data-hungry deep …

Developing deep neural networks to generate 3D scenes is a fundamental problem in
neural synthesis with immediate applications in architectural CAD, computer graphics, as …

We present the Semantic Robot Programming (SRP) paradigm as a convergence of robot
programming by demonstration and semantic mapping. In SRP, a user can directly program …

Implicit neural representations have become pivotal in robotic perception enabling robots to
comprehend 3D environments from 2D images. Given a set of camera poses and associated …

Comprehensive 3D scene understanding, both geometrically and semantically, is important
for real-world applications such as robot perception. Most of the existing work has focused …

The use of computer vision for product and assembly quality control is becoming ubiquitous
in the manufacturing industry. Lately, it is apparent that machine learning based solutions …

Reconstructing objects from real world data and rendering them at novel views is critical to
bringing realism, diversity and scale to simulation for robotics training and testing. In this …

BlenderProc2 is a procedural pipeline that can render realistic images for the training of
neural networks. Our pipeline can be employed in various use cases, including …

Synthetic data generation has become essential in last years for feeding data-driven
algorithms, which surpassed traditional techniques performance in almost every computer …