Yue Deng*

2 accepted papers

2024

Efficient Frequency-Domain Image Deraining with Contrastive Regularization

Ning Gao, Xingyu Jiang, Xiuhui Zhang, Yue Deng*

ECCV 2024poster

"Most current single image-deraining (SID) methods are based on the Transformer with global modeling for high-quality reconstruction. However, their architectures only build long-range features from the spatial domain, which suffers from a significant computational burden to keep effectiveness. Besi…

Cited by 14 Source ↗PDF ↗code ↗Scholar ↗

2024

When Fast Fourier Transform Meets Transformer for Image Restoration

Xingyu Jiang, Xiuhui Zhang, Ning Gao, Yue Deng*

ECCV 2024poster

"Natural images can suffer from various degradation phenomena caused by adverse atmospheric conditions or unique degradation mechanism. Such diversity makes it challenging to design a universal framework for kinds of restoration tasks. Instead of exploring the commonality across different degradatio…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗