3 papers
cs.CV2026
Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
Chunlei Zhang, Jiahao Xia, Yun Xiao +2
Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale arc…
cs.CV2024
Dynamic Disentangled Fusion Network for RGBT Tracking
Chenglong Li, Tao Wang, Zhaodong Ding +2
RGBT tracking usually suffers from various challenging factors of low resolution, similar appearance, extreme illumination, thermal crossover and occlusion, to name a few. Existing…
cs.CV2024
Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation
Andong Lu, Jiacong Zhao, Chenglong Li +2
Modality gap between RGB and thermal infrared (TIR) images is a crucial issue but often overlooked in existing RGBT tracking methods. It can be observed that modality gap mainly li…