6 papers
Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
Xinghua Huang, Zhixiong Yang, Chen Wu +6
A fundamental difficulty in all-in-one blind image restoration is that degradation is usually treated as an implicit factor hidden in degraded-to-clean mapping, rather than as an e…
Unlocking Optical Prior: Spectrum-Guided Knowledge Transfer for SAR Generalized Category Discovery
Jingyuan Xia, Ruikang Hu, Ye Li +3
Generalized Category Discovery (GCD) holds significant promise for the label-scarce Synthetic Aperture Radar (SAR) domain, yet its efficacy is severely constrained by the cross-mod…
Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
Chen Wu, Ling Wang, Zhuoran Zheng +6
Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state spa…
Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement
Derong Kong, Zhixiong Yang, Shengxi Li +4
Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization. While existing methods predominantly focus o…
Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation
Jingyuan Xia, Zhixiong Yang, Shengxi Li +4
Learning-based approaches have witnessed great successes in blind single image super-resolution (SISR) tasks, however, handcrafted kernel priors and learning based kernel priors ar…
A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution
Zhixiong Yang, Jingyuan Xia, Shengxi Li +5
Deep learning-based methods have achieved significant successes on solving the blind super-resolution (BSR) problem. However, most of them request supervised pre-training on labell…