DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing
DISTA-Net:动态紧密空间红外小目标解混
机构 * School of Computer Science, Nanjing University of Posts and Telecommunications(南京邮电大学计算机科学学院) ; VCIP, CS, Nankai University(南开大学) ; NKIARI, Futian, Shenzhen(深圳南山区NKIARI)
AI总结 DISTA-Net通过动态迭代收缩阈值网络实现紧密排列红外小目标的解混,首次提出该领域深度学习模型并建立开源生态系统。
Comments Accepted by ICCV 2025. This updated version fixed the bug in SSIM, while the conclusion remains the same