Results 41 to 50 of about 5,049,293 (271)

PromptStyle: Controllable Style Transfer for Text-to-Speech with Natural Language Descriptions [PDF]

Interspeech, 2023
Style transfer TTS has shown impressive performance in recent years. However, style control is often restricted to systems built on expressive speech recordings with discrete style categories.
Guanghou Liu, Yongmao Zhang, Yinjiao Lei, Yunlin Chen, Rui Wang, Zhifei Li, Linfu Xie   +6 more
semanticscholar   +1 more source

Aesthetic style transferring method based on deep neural network between Chinese landscape painting and classical private garden’s virtual scenario

International Journal of Digital Earth, 2023
Most of the existing virtual scenarios built for the digital protection of Chinese classical private gardens are too modern in expression style to show the aesthetic significance of their historical period.
Shuai Hong, Jie Shen, Guonian Lü, Xiaoyan Liu, Yirui Mao, Nina Sun, Long Tang   +6 more
doaj   +1 more source

Deep Learning-Based Motion Style Transfer Tools, Techniques and Future Challenges

Sensors, 2023
In the fourth industrial revolution, the scale of execution for interactive applications increased substantially. These interactive and animated applications are human-centric, and the representation of human motion is unavoidable, making the ...
Syed Muhammad Abrar Akber, Sadia Nishat Kazmi, Syed Muhammad Mohsin, Agnieszka Szczęsna   +3 more
doaj   +1 more source

Characterizing and Improving Stability in Neural Style Transfer [PDF]

, 2017
Recent progress in style transfer on images has focused on improving the quality of stylized images and speed of methods. However, real-time methods are highly unstable resulting in visible flickering when applied to videos.
Alahi, Alexandre, Fei-Fei, Li, Gupta, Agrim, Johnson, Justin   +3 more
core   +2 more sources

Evaluating prose style transfer with the Bible [PDF]

, 2018
In the prose style transfer task a system, provided with text input and a target prose style, produces output which preserves the meaning of the input text but alters the style.
Carlson, Keith, Riddell, Allen, Rockmore, Daniel   +2 more
core   +3 more sources

Neural Preset for Color Style Transfer [PDF]

Computer Vision and Pattern Recognition, 2023
In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed. Our method is based on two core designs.
Zhanghan Ke, Yuhao Liu, Lei Zhu, Nanxuan Zhao, Rynson W. H. Lau   +4 more
semanticscholar   +1 more source

Cycle consistent style transfer based on style-transition attention [PDF]

Journal of Hebei University of Science and Technology
In order to solve the problem that the existing art style transfer methods can not maintain high-quality image content and transform style patterns at the same time, a novel style-transition attention network (STANet) was introduced, which consists of ...
Rui[DK]’er ZHANG, Xiaohang BIAN, Siyuan LIU, Bin LIU, Jianwu LI, Jun LUO, Mingyue QI   +6 more
doaj   +1 more source

Style-Content-Aware Adaptive Normalization Based Pose Guided for Person Image Synthesis

IEEE Access, 2023
Most of the tasks based on pose-guided person image synthesis have obtained accurate target pose, but still have not obtained reasonable style texture mapping. In this paper, we propose a new two-stage network to decouple style and content, which aims to
Wei Wei, Xia Yang, Xiaodong Duan, Chen Guo   +3 more
doaj   +1 more source

IFFMStyle: High-Quality Image Style Transfer Using Invalid Feature Filter Modules

Sensors, 2022
Image style transfer is a challenging problem in computer vision which aims at rendering an image into different styles. A lot of progress has been made to transfer the style of one painting of a representative artist in real time, whereas less attention
Zhijie Xu, Liyan Hou, Jianqin Zhang
doaj   +1 more source

Demystifying Neural Style Transfer [PDF]

, 2017
Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains ...
Hou, Xiaodi, Li, Yanghao, Liu, Jiaying, Wang, Naiyan   +3 more
core   +1 more source