A Universal Scale-Adaptive Deformable Transformer for Image Restoration Across Diverse Artifacts
Abstract
Structured artifacts are semi-regular, repetitive patterns that closely intertwine with genuine image content, making their removal highly challenging. In this paper, we introduce the Scale-Adaptive Deformable Transformer, an network architecture specifically designed to eliminate such artifacts from images. The proposed network features two key components: a scale-enhanced deformable convolution module for modeling scale-varying patterns with abundant orientations and potential distortions, and a scale-adaptive deformable attention mechanism for capturing long-range relationships among repetitive patterns with different sizes and non-uniform spatial distributions. Extensive experiments show that our network consistently outperforms state-of-the-art methods in diverse artifact removal tasks, including image deraining, image demoireing, and image debanding.
Cite
Text
He et al. "A Universal Scale-Adaptive Deformable Transformer for Image Restoration Across Diverse Artifacts." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.01188Markdown
[He et al. "A Universal Scale-Adaptive Deformable Transformer for Image Restoration Across Diverse Artifacts." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/he2025cvpr-universal/) doi:10.1109/CVPR52734.2025.01188BibTeX
@inproceedings{he2025cvpr-universal,
title = {{A Universal Scale-Adaptive Deformable Transformer for Image Restoration Across Diverse Artifacts}},
author = {He, Xuyi and Quan, Yuhui and Xu, Ruotao and Ji, Hui},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {12731-12741},
doi = {10.1109/CVPR52734.2025.01188},
url = {https://mlanthology.org/cvpr/2025/he2025cvpr-universal/}
}