3 citations · 7 across the 22 of their papers we have counts for
7 papers · 1 filter
Hard, Yet Reducible: Controlled Forward Transfer for Synthetic Degradation Curation
Chunming He, Kailai Zhou, Jiaming Zuo +6
Selecting synthetic degradations for dense prediction requires an estimate of their training utility, the generalization gain they bring under a finite training budget. Clean and d…
PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing
Chengyu Fang, Chunming He, Yuelin Zhang +6
Real-world image dehazing (RID) aims to remove haze-induced degradation from real scenes. This task remains challenging due to non-uniform haze distribution, spatially varying colo…
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…
DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution
Zheng Chen, Ruofan Yang, Jin Han +5
Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the coupled space-time video super-…
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…
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…