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.


© 2020 ECCV

Ruofan Zhou and Majed El Helou's paper accepted to ECCV2020

— The paper "Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks" accepted to ECCV2020. IVRL members Ruofan Zhou and Majed El Helou will present their work at the online European Conference on Computer Vision between 23-28 August 2020.

© 2020 Hakgu Kim

IVRL welcomes a new member Hak Gu Kim

— Hak Gu Kim joined IVRL as a post-doctoral researcher. We wish you good luck on your research!

© 2020 EPFL

Congratulations to Dr. Ruofan Zhou !

— Ruofan Zhou received her PhD degree after her thesis defense on 29.06.2020.

© 2020 EPFL

IVRL welcomes a new member Berk Dogan

— Berk Dogan joined IVRL as a computer scientist. We wish you good luck!

© 2020 EECV

We released the image relighting dataset "VIDIT"

— We released the image relighting dataset VIDIT on May 13th. It is used for the AIM workshop competitions in ECCV 2020, starting the same date. Image relighting is fundamental for domain adaptation (data augmentation, normalization), photo montage and photo manipulation for aesthetics.

Leonardo Impett © Enrico Fontolan/Bibliotheca Hertziana

Leonardo Impett defends second EPFL Digital Humanities thesis

— Following an online defense on May 8th, Leonardo Impett became the second doctoral student to earn a PhD from the EDDH, the digital humanities doctoral program in the College of Humanities (CDH) Digital Humanities Institute (DHI).

© 2020 IEEE

Majed El Helou's paper accepted for publication in IEEE TIP

— The paper "Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning" accepted for publication in IEEE Transactions on Image Processing.

© 2020 EPFL

Three papers accepted to ICASSP2020

— The authors will present their works on 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 virtually between May 4 and May 8, 2020.

© 2020 CVPR

Edo Collins' paper accepted to CVPR 2020

— The paper "Editing in Style: Uncovering the Local Semantics of GANs" accepted to CVPR2020.

© 2020 CVPR IEEE

Deblina Bhattacharjee's paper accepted to CVPR 2020

— The paper "DUNIT- Detection based Unsupervised Image to Image Translation" accepted to CVPR2020.

All news

Archived News…