12 papers
Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion
Chunming He, Rihan Zhang, Fengyang Xiao +3
Biological learning proceeds from easy to difficult tasks, gradually reinforcing perception and robustness. Inspired by this principle, we address Context-Entangled Content Segment…
RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects
Chunming He, Rihan Zhang, Dingming Zhang +5
Concealed Object Segmentation (COS) encompasses a family of dense-prediction tasks, including camouflaged object detection, polyp segmentation, transparent object detection, and in…
UnfoldLDM: Degradation-Aware Unfolding with Iterative Latent Diffusion Priors for Blind Image Restoration
Chunming He, Rihan Zhang, Zheng Chen +6
Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited for blind image restoration (BIR).…
Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration
Fengyang Xiao, Peng Hu, Lei Xu +7
Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions. Existing methods typically depen…
QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration
Fengyang Xiao, Jingjia Feng, Peng Hu +6
Real-world image restoration (RWIR) is a highly challenging task due to the absence of clean ground-truth images. Many recent methods resort to pseudo-label (PL) supervision, often…
Nested Unfolding Network for Real-World Concealed Object Segmentation
Chunming He, Rihan Zhang, Dingming Zhang +3
Deep unfolding networks (DUNs) have recently advanced concealed object segmentation (COS) by modeling segmentation as iterative foreground-background separation. However, existing…