ACM MM 2020 Demo Paper Image and video restoration and compression

Filippo Mameli, Marco Bertini, Leonardo Galteri, Alberto Del Bimbo, Image and video restoration and compression artefact removal using a NoGAN approach

Our demo paper Filippo Mameli, Marco Bertini, Leonardo Galteri, Alberto Del Bimbo, Image and video restoration and compression artefact removal using a NoGAN approach has been accepted for publication at ACM Multimedia 2020.

Lossy image and video compression algorithms introduce several types of visual artefacts that reduce the visual quality of the compressed media.

In this work, we report results obtained using the NoGAN training approach and adapting the popular DeOldify architecture used for colorization, for image and video compression artefact removal and restoration.

My Kieu, Andrew D. Bagdanov, Marco Bertini, Alberto del Bimbo, Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery

ECCV 2020 Paper

Domain Adaptation for Pedestrian Detection

Hero for Florence

Hero for Florence

Homage to David: Saracino interprets Michelangelo

ICIAP2019 award

Best Student Paper Honorable Mention