SPAST: Arbitrary style transfer with style priors via pre-trained large-scale model
- 10 May 2025
- journal article
- Published by Elsevier in Neural Networks
- Vol. 189, 107556
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Ningbo Municipal Bureau of Science and Technology (2022Z167, 2023Z137)
- National Key Research and Development Program of China (62172365, 19ZDA197, 2021YFF0900604)
- Zhejiang University
- Ministry of Education of the People's Republic of China
- Key Research and Development Program of Zhejiang Province (2024C03263, LZ25F020006)
This publication has 30 references indexed in Scilit:
- DyArtbank: Diverse artistic style transfer via pre-trained stable diffusion and dynamic style prompt ArtbankKnowledge-Based Systems, 2025
- Intrinsic-style distribution matching for arbitrary style transferKnowledge-Based Systems, 2024
- Caster: Cartoon style transfer via dynamic cartoon style castingNeurocomputing, 2023
- CSAST: Content self-supervised and style contrastive learning for arbitrary style transferNeural Networks, 2023
- Cycle consistent network for end-to-end style transfer TTS trainingNeural Networks, 2021
- Uncorrelated feature encoding for faster image style transferNeural Networks, 2021
- ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows2021
- Image style transfer with collection representation space and semantic-guided reconstructionNeural Networks, 2020
- Arbitrary Style Transfer With Style-Attentional Networks2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018