In the training step, I found there is a step cropping image according camera_intrinsic and make principal point to be center of image in https://github.com/naver/dust3r/blob/main/dust3r/datasets/co3d.py#L100 . I wonder cropping is necessary? Is it OK if I just resize image(That is the principal point may not in the center of image ), because for my dataset, They will lose some information if cropped in the margin.
In the training step, I found there is a step cropping image according camera_intrinsic and make principal point to be center of image in https://github.com/naver/dust3r/blob/main/dust3r/datasets/co3d.py#L100 . I wonder cropping is necessary? Is it OK if I just resize image(That is the principal point may not in the center of image ), because for my dataset, They will lose some information if cropped in the margin.