Photo of Jonas Unger

Jonas Unger

Professor, Head of Division

Head of division - Media and Information Technology
Research leader – Visual and Interactive AI

Presentation

Professor Jonas Unger is leading the research efforts within Computer Graphics and Image Processing group in the division for Media and Information Technology at the department of Science and Technology. The vision of the group is to research and develop new theory and technology for computational imaging by fusing computer graphics,vision and sensors with human perception and machine learning to capture, digitize and reason about aspects of the world that have not been possible before. With a strong foundation in the theoretically oriented research, the group is active within a number of industrial and academic collaborations directed towards development of state-of-the-art applications ranging from 3D-reconstruction of scenes, photorealistic image synthesis and digitization of optical material properties to computer vision for heart surgery, AI driven diagnostics tools for medical applications, perceptual display algorithms, and software for autonomous systems such as self-driving cars and robot navigation.

A collage with examples of different technics used in computer graphics


Publications

2026

Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen (2026) Evaluating representation conditioned diffusion models: A comparative study of image-based representation encoders Journal of Visual Communication and Image Representation, Vol. 121, Article 104950 (Article in journal) https://dx.doi.org/10.1016/j.jvcir.2026.104950
Jiarong Gong, Jonas Unger, Ehsan Miandji (2026) Smaller and Faster 3DGS via Post-Training Dictionary Learning EG 2026 - POSTERS (Conference paper) https://dx.doi.org/10.2312/egp.20261016
Jens Nilsson, Jonas Unger, Gabriel Eilertsen (2026) Multi-Agent Reinforcement Learning for Conflict Resolution in Air Traffic Control With Delayed Actions IEEE Open Journal of Intelligent Transportation Systems, Vol. 7, p. 2037-2044 (Article in journal) https://dx.doi.org/10.1109/ojits.2026.3718458
Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen (2026) Representation-Conditioned Diffusion Models for Guided Training Data Generation Synthetic Data for Computer Vision Workshop (SynData4CV) (Conference paper)
Yifan Ding, Liu Xixi, Jonas Unger, Gabriel Eilertsen (2026) Enhancing out-of-distribution detection with extended logit normalization Proceedings of IEEE/CVF Conference on Computer vision and Pattern Recognition (CVPR) (Conference paper)

Research

News

Organisation