Research

My main interests currently are 3D reconstruction and generation, generative models, image processing, multimedia forensics and reproducible research.

Reproducible research

I am heavily invested in the IPOL (Image Processing On Line) journal and demo system for open science and reproducible research. In particular, I have been organizing the IPOL MLBriefs workshop and hackhathon since its creation. Continue reading Reproducible research

Positional Learning

I invented POsitional LeARning (Polar), a novel training scheme for CNNs that implicitly reveals underlying spatial or spectral information and can highlight its inconsistencies. Positional learning has already been applied successfully to AI-generated image detection, and mosaic inconsistency detection, for image forensics. Continue reading Positional Learning

Multimedia forensics

I detect fake images, that have been forged, manipulated or entirely AI-generated, by reverse-engineering the image and its processing pipeline. Continue reading Multimedia forensics

Image processing

Image and video processing is an underlying but central topic to most of my research. Continue reading Image processing