Open blueFeather111 opened 2 months ago
Before training.py - colmap generate cameras and images. Those images are corrected in perspective and size. So they are different from GT.
Before training.py - colmap generate cameras and images. Those images are corrected in perspective and size. So they are different from GT.
Thank you very much for your reply. I just used the colmap gui -> automatic reconstruction to get the sparse folder, no new images generated(still original images). I saw this issue https://github.com/colmap/colmap/issues/2282 about generating images using convert.py. I used convert.py instead to generate images and now they are the same.
when I overlap the gt image and the rendered image, I found they are not in the same location. I trained the truck for 10000 iterations, and use rendered.py to get the rendered image.
you can see there is a shift between them, is there something wrong? the truck is in TNT dataset.