Image and Visual Representation Lab ‐ EPFL

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.

News:

AI4VA workshop at ECCV 2024

Published:19.09.24 — IVRL and CVLab are organizing the AI4VA workshop in ECCV 2024 on September 29th.

Keynote of Prof. Sabine Süsstrunk at CoSeRa 2024

Published:19.09.24 — Sabine Süsstrunk will deliver a keynote presentation "On generating image and video hallucinations" at CoSeRa 2024 on September 20th.

Data Augmentation via Latent Diffusion for Saliency at ECCV 2024

Published:02.09.24 — 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”

Published:19.08.24 — 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).

6 posters from IVRL presented at ICCP 2024 in EPFL

Published:29.07.24 — 6 posters from IVRL were presented at ICCP 2024 in EPFL, including 1 spotlight poster.

Best Student Paper Award at ALIFE 2024

Published:27.07.24 — Our paper "NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata" received the Best Student Paper award at the Artificial Life Conference (ALIFE 2024).

IVRL at SIGGRAPH 2024

Published:26.07.24 — Two members of IVRL will attend SIGGRAPH 2024 in Denver from July 28th to August 1st. Dongqing Wang was selected to be part of the Rising Stars program of WiGRAPH, and Yitao Xu will present our work on Mesh Neural Cellular Automata.

"SINDER: Repairing the Singular Defects of DINOv2" at ECCV 2024

Published:25.07.24 — Our paper "SINDER: Repairing the Singular Defects of DINOv2" was accepted at the 2024 European Conference on Computer Vision (ECCC 2024)