Open zhihaoyi opened 2 days ago
Hi,
for the image stiching step, you could try UDIS2, I think you could as well obtain a corresponding M_s. BTW, if you have an already stiching image without M_s, you could consider using this function define_mask_zero_borders to generate one
Thank you for your information! I will definitely try it out!
Besides that, I am also wondering how to collect the training dataset. In the training dataset, we have rectangular images as GT and non-rectangular stitched images as inputs, but I am confused how we can obtain those pairs. Do we generate non-rectangular stitched images from GT using manually crafted motion fields?
hi, you could refer to Deep Rectangling for Image Stitching: A Learning Baseline for more detail about creating dataset.
Hi! That was a great work proposed by your team!
I am wondering how I am supposed to generate our own dataset from two individual images to a rectangle stitched image with M_s?