The project I participated in as a core member involves infrared characteristic modeling, infrared enhancement, and multi-modal fusion.
A self-supervised image denoising and destriping framework based on blind-spot regularization. The framework transforms the overall denoising and destriping problem into a modeling task for two spatially correlated signals: image and stripe.
To address the challenges faced in paired data collection, we propose a modeling method for infrared characteristics, aimed at simulating the degradation from high-quality infrared images to low-quality infrared images.
Through adversarial semantic guidance technology, a controllable infrared and visible light image fusion method for salient targets is constructed.
The deployment and optimization of deep models on edge computing platforms aim to achieve real-time and robust infrared target detection.