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

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

© 2025 EPFL

Webinar held by Dr. Quentin Bammey at IEEE SPS

— Dr. Quentin Bammey will deliver a webinar at the IEEE Signal Processing Society (IEEE SPS) on May 6th. 

© 2025 EPFL-UNIL

Arts & Sciences collaboration and theater play

— IVRL collaborated with La Grange (UNIL) and the artistic team of Marielle Pinsard. The team of artists will perform a work-in-progress performance of their future play "Il était une fois la neige", in French, at the local theater of UNIL, La Grange, on Saturday, March 29th, 2025.

© 2024 EPFL

IVRL welcomes a new member Quentin Bammey

— Quentin Bammey joined IVRL as a post-doctoral researcher.

© 2024 EPFL

IVRL at NeurIPS 2024

— Yitao Xu, Tong Zhang, Sabine Süsstrunk, AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer, NeurIPS 2024.

© 2024 EPFL

Zhuoqian Yang passed his candidacy exam

— Zhuoqian Yang passed his candidacy exam entitled "Diffusion Models for Neural Network Weight Representation" .

© 2024 EPFL

AI4VA workshop at ECCV 2024

— IVRL and CVLab are organizing the AI4VA workshop in ECCV 2024 on September 29th. 

© 2024 EPFL

Keynote of Prof. Sabine Süsstrunk at CoSeRa 2024

— Sabine Süsstrunk will deliver a keynote presentation "On generating image and video hallucinations" at CoSeRa 2024 on September 20th.

© 2024 EPFL/Bahar Aydemir

Data Augmentation via Latent Diffusion for Saliency at ECCV 2024

— Our paper "Data Augmentation via Latent Diffusion for Saliency Prediction" was accepted at the 2024 European Conference on Computer Vision (ECCV 2024).

A composite image of the remnant of supernova 1181 © NASA/CHANDRA/WISE. ESA/XMM, MDM/R.Fessen (Dartmouth College), PAN-STARRS

“When imaging advances, science advances”

— Sabine Süsstrunk, an expert in scientific photography, has seen first-hand the amazing progress in imaging technology over the past 40 years. And now her field is being upended by artificial intelligence (AI).

All news

Archived News…