REST: A resolution preserving network for photorealistic style transfer via semantic distillation
Authors:
- Jing HuoJHJing Huo
- Zheng GuZGZheng Gu
- Jiulin ZhangJZJiulin Zhang
- Xiangde LiuXLXiangde Liu
- Shiyin JinSJShiyin Jin
- Pinzhuo TianPTPinzhuo Tian
- Wenbin LiWLWenbin Li
- Jing WuJWJing Wu
- Yu-Kun LaiYLYu-Kun Lai
- Yang GaoYang Gao
- 8 November 2025
- journal article
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 262
Abstract
No abstract availableFunding Information
- Nanjing University (KFKT2025B73)
- Jiangsu Province Natural Science Foundation (BK20243051)
- China Association for Science and Technology (2023QNRC001)
- National Natural Science Foundation of China (62192783)
- National Natural Science Foundation of China (62276128)
- Fundamental Research Funds for the Central Universities (14380128)
- Shenzhen University
- State Key Laboratory of Novel Software Technology
- Fundamental Research Funds for the Central Universities
This publication has 23 references indexed in Scilit:
- Rethink arbitrary style transfer with transformer and contrastive learningComputer Vision and Image Understanding, 2024
- Towards efficient image and video style transfer via distillation and learnable feature transformationComputer Vision and Image Understanding, 2024
- A Closed-Form Solution to Photorealistic Image Stylization2018
- A Style-Aware Content Loss for Real-Time HD Style Transfer2018
- Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields2018
- Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis2017
- Deep Photo Style Transfer2017
- Diversified Texture Synthesis with Feed-Forward Networks2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Color transfer between imagesIEEE Computer Graphics and Applications, 2001