Capece N., Banterle F., Cignoni P., Ganovelli F., Erra U., Potel M.
computer graphics Software Computer Graphics and Computer-Aided Design
We introduce a novel algorithm that turns a flash selfie taken with a smartphone into a studio-like photograph with uniform lighting. Our method uses a convolutional neural network trained on a set of pairs of photographs acquired in a controlled environment. For each pair, we have one photograph of a subject's face taken with the camera flash enabled and another one of the same subject in the same pose illuminated using a photographic studio-lighting setup. We show how our method can amend lighting artifacts introduced by a close-up camera flash, such as specular highlights, shadows, and skin shine.
Source: IEEE computer graphics and applications 40 (2020): 140–147. doi:10.1109/MCG.2019.2958274
Publisher: National Computer Graphics Association,, [Los Alamitos, CA] , Stati Uniti d'America
@article{oai:it.cnr:prodotti:424580, title = {Turning a Smartphone Selfie into a Studio Portrait}, author = {Capece N. and Banterle F. and Cignoni P. and Ganovelli F. and Erra U. and Potel M.}, publisher = {National Computer Graphics Association,, [Los Alamitos, CA] , Stati Uniti d'America}, doi = {10.1109/mcg.2019.2958274}, journal = {IEEE computer graphics and applications}, volume = {40}, pages = {140–147}, year = {2020} }