CINECA IRIS Institutional Research Information System

IRIS è l'Anagrafe della ricerca dell'Università degli Studi di Trento, e ha lo scopo di raccogliere, documentare, conservare e diffondere, anche ad accesso aperto, la produzione scientifica degli autori afferenti all'Università degli Studi di Trento.

Manipulating visual attributes of images through human-written text is a very challenging task. On the one hand, models have to learn the manipulation without the ground truth of the desired output. On the other hand, models have to deal with the inherent ambiguity of natural language. Previous research usually requires either the user to describe all the characteristics of the desired image or to use richly-annotated image captioning datasets. In this work, we propose a novel unsupervised approach, based on image-to-image translation, that alters the attributes of a given image through a command-like sentence such as "change the hair color to black". Contrarily to state-of-the-art approaches, our model does not require a human-annotated dataset nor a textual description of all the attributes of the desired image, but only those that have to be modified. Our proposed model disentangles the image content from the visual attributes, and it learns to modify the latter using the textual description, before generating a new image from the content and the modified attribute representation. Because text might be inherently ambiguous (blond hair may refer to different shadows of blond, e.g. golden, icy, sandy), our method generates multiple stochastic versions of the same translation. Experiments show that the proposed model achieves promising performances on two large-scale public datasets: CelebA and CUB. We believe our approach will pave the way to new avenues of research combining textual and speech commands with visual attributes.

Describe What to Change: A Text-guided Unsupervised Image-to-image Translation Approach / Liu, Y.; De Nadai, M.; Cai, D.; Li, H.; Alameda-Pineda, X.; Sebe, N.; Lepri, B.. - (2020), pp. 1357-1365. ((Intervento presentato al convegno 28th ACM International Conference on Multimedia, MM 2020 tenutosi a usa nel 2020.

Powered by IRIS-about IRIS-Utilizzo dei cookie

 Copyright © 2021