PhD Position in Computer Vision

Positions: We have an opening for a PhD position in computer vision. The main research topic of this position is 3D object reconstruction and animation from real videos. This project is based on unsupervised learning, that is, it uses datasets that do not have human labeling/annotation (eg, text, bounding boxes, pose, skeletons) and does not rely on prior models built through supervision (eg, segmentation methods, depth map predictors, object classifiers). One of the main challenges is to handle the deformation of objects since the object categories are unknown. Research will be performed in the Computer Vision Group at the University of Bern. The position can start from January 1, 2025, at the earliest and will be filled as soon as a suitable candidate is found. 

Your profile: We are looking for a highly motivated candidate, who is eager to get involved in cutting edge, creative research. You hold a Master of Science in Computer Science, Mathematics or Engineering, with a solid background in machine learning and computer vision. You have excellent skills in applied mathematics, in probability theory, and a programming language (e.g., Python, C/C++). You have a solid background in Deep Learning, and you are already a proficient programmer in one of the main Deep Learning libraries (e.g., TensorFlow, PyTorch). We expect fluent communication skills in English.

What we offer: You will be part of a team of academic researchers working on state-of-the-art technologies for machine learning and computer vision. You will have the chance to contribute to and participate in the international research community. We are in Bern in the core of Switzerland, one of the cities with the highest quality of life worldwide. You will receive a very competitive salary (a base salary for the research + a separate teaching assistance salary) and be given financial support to attend training courses and international conferences.

Application and further information: 
Deadline: December 20, 2024
Applications must be submitted to Prof Paolo Favaro, through the submission website link
http://cvg.unibe.ch/vacancies/
Applications submitted directly via email will not be considered.