8 papers
From Physical Degradation Models to Task-Aware All-in-One Image Restoration
Hu Gao, Xiaoning Lei, Xichen Xu +2
All-in-one image restoration aims to adaptively handle multiple restoration tasks with a single trained model. Although existing methods achieve promising results by introducing pr…
Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution
Hu Gao, Xiaoning Lei, Xichen Xu +2
Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degrad…
Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation
Hu Gao, Xiaoning Lei, Ying Zhang +3
Image restoration (IR) aims to recover clean images from degraded observations. Despite remarkable progress, most existing methods focus on a single degradation type, whereas real-…
STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment
Xichen Xu, Yanshu Wang, Jinbao Wang +5
Segmentation-oriented Industrial Anomaly Synthesis (SIAS) plays a pivotal role in enhancing the performance of downstream anomaly segmentation, as it provides an effective means of…
FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
Xichen Xu, Yanshu Wang, Jinbao Wang +4
Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial…
MBMamba: When Memory Buffer Meets Mamba for Structure-Aware Image Deblurring
Hu Gao, Xiaoning Lei, Xichen Xu +2
The Mamba architecture has emerged as a promising alternative to CNNs and Transformers for image deblurring. However, its flatten-and-scan strategy often results in local pixel for…