Neural style transfer: A review

Y **g, Y Yang, Z Feng, J Ye, Y Yu… - IEEE transactions on …, 2019‏ - ieeexplore.ieee.org
The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks
(CNNs) in creating artistic imagery by separating and recombining image content and style …

Deep learning for image colorization: Current and future prospects

S Huang, X **, Q Jiang, L Liu - Engineering Applications of Artificial …, 2022‏ - Elsevier
Image colorization, as an essential problem in computer vision (CV), has attracted an
increasing amount of researchers attention in recent years, especially deep learning-based …

NeRF-Art: Text-Driven Neural Radiance Fields Stylization

C Wang, R Jiang, M Chai, M He… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
As a powerful representation of 3D scenes, the neural radiance field (NeRF) enables high-
quality novel view synthesis from multi-view images. Stylizing NeRF, however, remains …

Ccpl: Contrastive coherence preserving loss for versatile style transfer

Z Wu, Z Zhu, J Du, X Bai - European Conference on Computer Vision, 2022‏ - Springer
In this paper, we aim to devise a universally versatile style transfer method capable of
performing artistic, photo-realistic, and video style transfer jointly, without seeing videos …

Deep exemplar-based colorization

M He, D Chen, J Liao, PV Sander, L Yuan - ACM Transactions on …, 2018‏ - dl.acm.org
We propose the first deep learning approach for exemplar-based local colorization. Given a
reference color image, our convolutional neural network directly maps a grayscale image to …

Avatar-net: Multi-scale zero-shot style transfer by feature decoration

L Sheng, Z Lin, J Shao, X Wang - Proceedings of the IEEE …, 2018‏ - openaccess.thecvf.com
Zero-shot artistic style transfer is an important image synthesis problem aiming at
transferring arbitrary style into content images. However, the trade-off between the …

Geometry-consistent generative adversarial networks for one-sided unsupervised domain map**

H Fu, M Gong, C Wang… - Proceedings of the …, 2019‏ - openaccess.thecvf.com
Unsupervised domain map** aims to learn a function GXY to translate domain X to Y in
the absence of paired examples. Finding the optimal GXY without paired data is an ill-posed …

Parallax attention for unsupervised stereo correspondence learning

L Wang, Y Guo, Y Wang, Z Liang, Z Lin… - IEEE transactions on …, 2020‏ - ieeexplore.ieee.org
Stereo image pairs encode 3D scene cues into stereo correspondences between the left
and right images. To exploit 3D cues within stereo images, recent CNN based methods …

Cross view capture for stereo image super-resolution

X Zhu, K Guo, H Fang, L Chen… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Stereo image super-resolution exploits additional features from cross view image pairs for
high resolution (HR) image reconstruction. Recently, several new methods have been …