3 papers
cs.CV2025
CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking
Hao Li, Yuhao Wang, Xiantao Hu +4
RGB-Thermal (RGBT) tracking aims to exploit visible and thermal infrared modalities for robust all-weather object tracking. However, existing RGBT trackers struggle to resolve moda…
cs.CV2025
When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
Wenxuan Fang, Jili Fan, Chao Wang +5
Adverse Weather Image Restoration (AWIR) is a highly challenging task due to the unpredictable and dynamic nature of weather-related degradations. Traditional task-specific methods…
cs.CV2025
Learning Multi-scale Spatial-frequency Features for Image Denoising
Xu Zhao, Chen Zhao, Xiantao Hu +3
Recent advancements in multi-scale architectures have demonstrated exceptional performance in image denoising tasks. However, existing architectures mainly depends on a fixed singl…