Michael Felsberg

Innovative methods for real-time area coverage using robotic systems.

New approaches improve accuracy in detecting keypoints for 3D scenes.

SeTformer improves efficiency in processing images and language.

MobiLlama offers efficient language processing for devices with limited resources.

New framework improves video searches by combining visuals and detailed language descriptions.

A new simulator aims to improve safety standards in self-driving car technology.

This study focuses on improving robot training by transferring reinforcement learning from simulation to real environments.

Soft-IntroVAE enhances VAEs with prior learning for better data generation.

This article discusses a new method to enhance image matching using affine steerers.