1.
Dediu, Marius; Vasile, Costin-Emanuel; Bira, Calin
Deep Layer Aggregation Architectures for Photorealistic Universal Style Transfer Journal Article
In: SENSORS, vol. 23, no. 9, 2023.
Abstract | Links | BibTeX | Tags: deep learning; photorealistic; style transfer; deep layer aggregation
@article{WOS:000988076400001,
title = {Deep Layer Aggregation Architectures for Photorealistic Universal Style
Transfer},
author = {Marius Dediu and Costin-Emanuel Vasile and Calin Bira},
doi = {10.3390/s23094528},
year = {2023},
date = {2023-05-01},
journal = {SENSORS},
volume = {23},
number = {9},
publisher = {MDPI},
address = {ST ALBAN-ANLAGE 66, CH-4052 BASEL, SWITZERLAND},
abstract = {This paper introduces a deep learning approach to photorealistic
universal style transfer that extends the PhotoNet network architecture
by adding extra feature-aggregation modules. Given a pair of images
representing the content and the reference of style, we augment the
state-of-the-art solution mentioned above with deeper aggregation, to
better fuse content and style information across the decoding layers. As
opposed to the more flexible implementation of PhotoNet (i.e.,
PhotoNAS), which targets the minimization of inference time, our method
aims to achieve better image reconstruction and a more pleasant
stylization. We propose several deep layer aggregation architectures to
be used as wrappers over PhotoNet, to enhance the stylization and
quality of the output image.},
keywords = {deep learning; photorealistic; style transfer; deep layer aggregation},
pubstate = {published},
tppubtype = {article}
}
This paper introduces a deep learning approach to photorealistic
universal style transfer that extends the PhotoNet network architecture
by adding extra feature-aggregation modules. Given a pair of images
representing the content and the reference of style, we augment the
state-of-the-art solution mentioned above with deeper aggregation, to
better fuse content and style information across the decoding layers. As
opposed to the more flexible implementation of PhotoNet (i.e.,
PhotoNAS), which targets the minimization of inference time, our method
aims to achieve better image reconstruction and a more pleasant
stylization. We propose several deep layer aggregation architectures to
be used as wrappers over PhotoNet, to enhance the stylization and
quality of the output image.
universal style transfer that extends the PhotoNet network architecture
by adding extra feature-aggregation modules. Given a pair of images
representing the content and the reference of style, we augment the
state-of-the-art solution mentioned above with deeper aggregation, to
better fuse content and style information across the decoding layers. As
opposed to the more flexible implementation of PhotoNet (i.e.,
PhotoNAS), which targets the minimization of inference time, our method
aims to achieve better image reconstruction and a more pleasant
stylization. We propose several deep layer aggregation architectures to
be used as wrappers over PhotoNet, to enhance the stylization and
quality of the output image.