paper-with-me

홈 › Papers

Unified Style Transfer

2021-10-20 · Guanjie Huang, Hongjian He, Xiang Li, Xingchen Li, Ziang Liu

Currently, it is hard to compare and evaluate different style transfer algorithms due to chaotic definitions of style and the absence of agreed objective validation methods in the study of style transfer. In this paper, a novel approach, the Unified Style Transfer (UST) model, is proposed. With the introduction of a generative model for internal style representation, UST can transfer images in two approaches, i.e., Domain-based and Image-based, simultaneously. At the same time, a new philosophy based on the human sense of art and style distributions for evaluating the transfer model is presented and demonstrated, called Statistical Style Analysis. It provides a new path to validate style transfer models' feasibility by validating the general consistency between internal style representation and art facts. Besides, the translation-invariance of AdaIN features is also discussed.

📄 PDF Abstract BibTeX arXiv:2110.10481

Code (1)

sonnguyen129/deep-feature-rotation tf

Tasks

PhilosophyStyle TransferTranslation

Similar Papers 제목 키워드 기반

STEER: Unified Style Transfer with Expert Reinforcement

2023-11-13 · Skyler Hallinan, Faeze Brahman, Ximing Lu, JaeHun Jung 외

While text style transfer has many applications across natural language processing, the core premise of transferring from a single source style is unrealistic in a real-world setting. In this work, we focus on arbitrary …

Style TransferText Style Transfer

MM-TTS: Multi-modal Prompt based Style Transfer for Expressive Text-to-Speech Synthesis

2023-12-17 · Wenhao Guan, Yishuang Li, Tao Li, Hukai Huang 외

The style transfer task in Text-to-Speech refers to the process of transferring style information into text content to generate corresponding speech with a specific style. However, most existing style transfer approaches…

Speech SynthesisStyle Transfertext-to-speechText to Speech+1

A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning

2023-03-09 · Yuxin Zhang, Fan Tang, WeiMing Dong, Haibin Huang 외

We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style transfer models, e.g., CNN-based, ViT-ba…

Contrastive LearningRepresentation LearningStyle Transfer

A Unified Framework for Generalizable Style Transfer: Style and Content Separation

2018-06-13 · Yexun Zhang, Ya zhang, Wenbin Cai

Image style transfer has drawn broad attention in recent years. However, most existing methods aim to explicitly model the transformation between different styles, and the learned model is thus not generalizable to new s…

DecoderMulti-Task LearningStyle Transfer

MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Reference

2024-09-09 · Jiancheng Huang, Yu Gao, Zequn Jie, Yujie Zhong 외

In this paper, we introduce MRStyle, a comprehensive framework that enables color style transfer using multi-modality reference, including image and text. To achieve a unified style feature space for both modalities, we …

Style Transfer