by Adrien Deliege
Disclaimer: the images have been compressed during the publication of this article. All high-quality images are available here.
This post summarizes some works carried out on Maria Giulia Dondero’s F.R.S.-FNRS research project “Towards a Genealogy of Visual Forms”.
Background of the project. The project aims at analyzing, quantifying, clustering, characterizing the evolution of “forms” in the broad sense, that have been represented in large corpuses of paintings throughout centuries, up to modern art such as in fashion photography. For that purpose, the project builds upon recent computer vision techniques powered by deep learning-based models trained on generic large-scale datasets. The interaction between these two worlds, computer vision on one hand, art analysis on the other hand, benefits them both, by producing insights on the capabilities and limitations of the former in the artistic domain, and by resulting in novel ways of revisiting the latter.
This post can be decomposed into 3 parts: (1) an introduction to pose estimation in computer vision and the model used, (2) an introduction to PixPlot as a visualization tool, (3) a presentation of results for the task of retrieving “similar” images to a query image.
Continuer la lecture de « Advances on the F.R.S.-FNRS research project “Towards a Genealogy of Visual Forms” : On character poses in paintings »