
I study visual media compression: I'm passionate about developing efficient representations of all kinds of visual media, including still images and video, but also novel modalities, such as augmented and virtual reality, plenoptic or holographic imaging, and so on.
A distinctive feature of my work is that I heavily rely on machine learning and end-to-end optimization. Machine learning can not only improve compression algorithms by adapting them better to the data, but we can also use machine learning to explore better models of visual perception. Understanding how humans perceive visual scenes can lead to much improved compression results.
A bit about my background: I defended my master's and doctoral theses on signal processing and image compression under the supervision of Jens-Rainer Ohm at RWTH Aachen University in 2007 and 2012, respectively. This was followed by a brief collaboration with Javier Portilla at CSIC in Madrid, Spain, and a postdoctoral fellowship at New York University’s Center for Neural Science with Eero P. Simoncelli, where I studied the relationship between perception and image statistics. While there, I pioneered using machine learning for end-to-end optimized image compression – this work ultimately led to the JPEG AI standard, finalized in 2025. From 2017 to 2024, I deepened my ties to industry as a Research Scientist at Google, continuing in the same line of research. I’ve served as a reviewer for top-tier publications in both machine learning and image processing, such as NeurIPS, ICLR, ICML, Picture Coding Symposium, and several IEEE Transactions journals. I have been active as a co-organizer of the annual Challenge on Learned Image Compression (CLIC) since 2018, and on the program committee of the Data Compression Conference (DCC) since 2022.