Machine learning meets physical models of image formation for photography and astronomy applications

Jean Ponce

Ecole normale supérieure, FRA & Inria, USA

Abstract

We live in an era of data-driven approaches to image analysis, where modeling is sometimes considered obsolete. I will propose in this presentation giving back to accurate physical models of image formation their rightful place next to machine learning in the overall processing and interpretation pipeline, and discuss two applications: super-resolution and high-dynamic range imaging from raw photographic bursts, and exoplanet detection and characterization in direct imaging at high contrast.