← Search

Xiangpeng Tian

2 accepted papers

2025

Degradation-Aware Feature Perturbation for All-in-One Image Restoration

CVPR 2025poster

All-in-one image restoration aims to recover clear images from various degradation types and levels with a unified model. Nonetheless, the significant variations among degradation types present challenges for training a universal model, often resulting in task interference, where the gradient update…

2024

Unsupervised Blind Image Deblurring Based on Self-Enhancement

CVPR 2024poster

Significant progress in image deblurring has been achieved by deep learning methods especially the remarkable performance of supervised models on paired synthetic data. However real-world quality degradation is more complex than synthetic datasets and acquiring paired data in real-world scenarios po…

Cited by 10SourcePDFScholar