Image and Visual Representation Lab

Welcome to IVRL

IVRL Logo

 

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.

News:

© 2025 EPFL

Congratulations to Dr. Yufan Ren!

— Yufan Ren received his PhD degree after his thesis defense on 12.11.2025.

© 2025 EPFL

Congratulations to Dr. Dongqing Wang!

— Dongqing Wang received her PhD degree after her thesis defense on 05.09.2025.

© 2025 EPFL

Best Poster Award at BMVC 2025

— Our team received the Best Poster Award at BMVC 2025 for the paper "Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata". 

Sabine Süsstrunk © 2025 EPFL/Alain Herzog - CC-BY-SA 4.0

Sabine Süsstrunk wins UK Royal Photographic Society Award

— IC Dean and Director of the Imaging and Visual Representation Laboratory has been recognized with the 2025 Royal Photographic Society Award for Imaging Science.

© 2025 EPFL

Deepfake Booth at AI for Good and EHF 2025

— Dr. Quentin Bammey presented the Deepfake Booth at the AI for Good summit and the European Humanitarian Forum (EHF).

© 2025 EPFL

Join us for a Reproducible Research Session at Gretsi 2025!

— Dr. Quentin Bammey will be present at Gretsi 2025 for a special session on reproducible research. 

© 2025 EPFL

Congratulations to Dr. Ehsan Pajouheshgar!

— Ehsan Pajouheshgar received his PhD degree after his thesis defense on 01.07.2025.

Sabine Süsstrunk © 2025 EPFL/Alain Herzog - CC-BY-SA 4.0

Sabine Süsstrunk appointed new IC School dean

— Head of the Images and Visual Representation Laboratory, Professor Süsstrunk will take the helm of the School of Computer and Communication Sciences in September.

© iStock

Staking out a path to trustworthy AI

— Generative artificial intelligence (GenAI) suffers from several types of biases that reflect human failings. How can we avoid being tricked?

© 2025 EPFL

A paper from IVRL will appear in CVPR 2025

— Yufan Ren, Zicong Jiang, Tong Zhang, Søren Forchhammer, Sabine Süsstrunk, FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing, CVPR 2025

All news

Archived News…