Image and Visual Representation Lab

Welcome to IVRL



The Image and Visual Representation Lab (IVRL) performs research that is primarily focused on the capture, analysis, and reproduction of color images. Aiming to improve everyone’s photographic experience, we develop algorithms and systems that help us understand, process, and measure images.

Our research areas are computational photography, color image processing, computer vision, and image quality.


AI generated image © 2023 EPFL/Peter Grönquist - CC-BY-SA 4.0

Comics in the new age of artificial intelligence

— Cut/Paste, a new exhibition at EPFL Pavilions, Pavilion A, delves into the history of comics and showcases how artificial intelligence is changing the art and adapting classic 1950s narratives for today’s varied mediums.

© 2023 EPFL

Professor Sabine Süsstrunk Delivered a Plenary Presentation at ICIP

— Professor Sabine Süsstrunk delivered a plenary presentation "On Generating Image and Video Hallucinations" at the IEEE International Conference on Image Processing (ICIP 2023). 

© 2023 EPFL

Three papers from IVRL will appear in ICCV 2023

— Three papers from IVRL will appear in ICCV 2023.

© 2023 EPFL

Congratulations to Dr. Deblina Bhattacharjee !

— Deblina Bhattacharjee received her PhD degree after her thesis defense on 18.07.2023.

© 2023 EPFL

IVRL Summer BBQ Outing

— IVRL members went to Vidy beach for a BBQ outing

© 2023 EPFL

IVRL welcomes a new member Raphaël Achddou

— Raphaël Achddou joined IVRL as a post-doctoral researcher.

Photo taken at EPFL Pavilions, of the exhibition "Deep Fakes: Art and Its Double" © Alain Herzog / EPFL

No quick fix for targeting misinformation on the internet

— Sabine Süsstrunk and Karl Aberer, two EPFL professors, emphasize the role of human action – and not technology – in curbing misinformation.

© 2023 EPFL

EPFL OpenDays: The Dangers of DeepFakes

— The DeepFakes Demo will be run by Peter Grönquist and Professor Sabine Süsstrunk on EPFL OpenDays, at the BC building. 

© 2023 EPFL

Our paper on point cloud SSL will appear in CVPR 2023

— The paper "Spatiotemporal Self-supervised Learning for Point Clouds in the Wild" by Yanhao Wu, Tong Zhang, Wei Ke, Sabine Süsstrunk, and Mathieu Salzmann is accepted to CVPR2023.

© 2023 EPFL

Our paper on implicit reconstruction will appear in CVPR 2023

— The paper "VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction" by Yufan Ren, Fangjinhua Wang, Tong Zhang, Marc Pollefeys, and Sabine Süsstrunk is accepted to CVPR2023.

All news

Archived News…