YanpingLi
YanpingLi
can I have a look at your paper, really interested in this area.
I also have this problem.Have you solved it?
> 配准是通过手动在两张图上标出特征点对，计算仿射变换矩阵，将一张图warp到另一张图的坐标系下，实现配准，最后将两张图的共同区域裁剪下来，resize到同一分辨率（保证长宽比不变），如果需要可以share给你一份我用的代码 你好，最近也在想红外-可见光图像对齐的方法，可不可以借鉴一下你的做法，十分感谢！[email protected]
and the gm_cls_loss, do not understand
The global matcher cls loss is different from what’s in the paper?
discretized into a two-dimensional grid?