Huo, Jing, Gu, Zheng, Zhang, Jiulin, Liu, Xiangde, Jin, Shiyin, Tian, Pingzhuo, Li, Wenbin, Wu, Jing  ORCID: https://orcid.org/0000-0001-5123-9861, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680 and Gao, Yang
2025.
REST: A resolution preserving metwork for photorealistic style transfer via semantic distillation.
Computer Vision and Image Understanding
262
, 104544.
10.1016/j.cviu.2025.104544
|
Preview |
PDF
- Accepted Post-Print Version
Available under License Creative Commons Attribution. Download (15MB) | Preview |
Abstract
Photorealistic style transfer aims to adapt the style of a reference image to a content image while preserving photorealism. Existing methods primarily rely on downsampling auto-encoders, which sacrifices spatial details due to the reduced feature map resolution and leads to artifacts. To address this problem, we propose a Resolution-preserving nEtwork for Style Transfer (REST) to maintain full spatial resolution during stylization. Our framework employs a resolution-preserving (RP) network (RPNet) that retains input resolution, effectively preserving fine details. Although RP features capture intricate spatial information, their reliance on high-resolution processing can limit semantic depth. To enhance feature representation, we introduce a semantic distillation module that transfers hierarchical patterns from VGG features into RPNet, ensuring balanced detail and semantic fidelity. Combined with advanced style transfer blocks, REST achieves photorealistic results with improved efficiency. Experiments show improved performance and faster processing over existing photorealistic style transfer approaches.
| Item Type: | Article |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Additional Information: | RRS policy applied. |
| Publisher: | Elsevier |
| ISSN: | 1077-3142 |
| Date of First Compliant Deposit: | 27 November 2025 |
| Date of Acceptance: | 16 October 2025 |
| Last Modified: | 27 Nov 2025 10:15 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/182469 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions