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.


© 2021 EPFL

Video compression patent and licensing

— We released an online demo of our extreme video completion method. Our technology is very energy and time-efficient on the encoder side (we require practically 0 computation and no specialized hardware like typical DCT-based encoders), it can reach extreme compression rates with complete rate flexibility and can achieve better visual reconstruction at these rates compared with the MPEG-4 H264 standard. This makes it ideal for instance for video-transmitting IoT devices, surveillance cameras, drone transmission, or emergency deployment transmission where bandwidth is very limited. Users can visualize different results and test with their own videos too on: For the more technically curious readers, we have an associated publication in the leading signal processing conference IEEE ICASSP that can be accessed here:

© 2021 CVPR

Depth-guided image relighting NTIRE workshop at CVPR

— IVRL members Majed El Helou and Ruofan Zhou co-organised this workshop, using the VIDIT dataset with geometry information. You can access the challenge paper here. 250 participants registered from various research labs, companies, and universities internationally. 

© 2021 EPFL

We released the image relighting dataset "VIDIT"

— We released depth information for our image relighting dataset VIDIT. It is used for the NTIRE workshop competitions in CVPR 2021 Image relighting is fundamental for domain adaptation (data augmentation, normalization), photo montage and photo manipulation for aesthetics.

© 2021 EPFL

ICIP 2021 – IEEE International Conference on Image Processing

— Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion by Xiaoqi Ma, Xiaoyu Lin, Majed El Helou, Sabine Süsstrunk accepted into ICIP 2021 – IEEE International Conference on Image Processing.

© 2021 EPFL

Congratulations to Dr. Majed El Helou !

— Majed El Helou received his PhD degree after his thesis defense on 26.03.2021.

© 2021 EPFL

Does computer science still have a ‘woman problem'?

— International Women’s Day – Three female professors working in EPFL’s School of Computer and Communication Sciences talk equality, men’s role in changing the world and the need to rebrand this ‘field of the future’ to attract more diverse talent. 

© 2021 EPFL

IVRL welcomes a new member Tong Zhang

— Tong Zhang joined IVRL as a postdoctoral researcher.

© 2020 Neurips

Chen Liu's paper accepted to NeurIPS 2020

— The paper “On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them” is accepted to NeurIPS 2020. IVRL member Chen Liu will present this work at the 34th Conference on Neural Information Processing Systems, which will be held online between 6th and 12th December 2020.

© 2020 EPFL

Congratulations to Dr. Marjan Shahpaski !

— Marjan Shahpaski received his PhD degree after his thesis defense on 28.08.2020.

Frédéric Kaplan © Alain Herzog

Frédéric Kaplan named director of Digital Humanities Institute

— College of Humanities (CDH) professor Frédéric Kaplan, head of the Laboratory for Digital Humanities (DHLab), has been named director of the CDH’s Digital Humanities Institute (DHI) as of October 1st, 2020.

All news

Archived News…