Open yuliangguo opened 10 months ago
https://github.com/google-research/nerf-from-image/blob/fddf72a8bc7b64307fad146f9a7b39d8df56a915/lib/pose_utils.py#L60C8-L60C8
The transform tform_cam2world[:, :3, 1:] = -1 seem to also reverse the sign of the translation. Should only the 2nd, and 3rd axis of the camra orientation be changed, meaning form_cam2world[:, :3, 1:3] = -1 is the right way?
https://github.com/google-research/nerf-from-image/blob/fddf72a8bc7b64307fad146f9a7b39d8df56a915/lib/pose_utils.py#L60C8-L60C8
The transform tform_cam2world[:, :3, 1:] = -1 seem to also reverse the sign of the translation. Should only the 2nd, and 3rd axis of the camra orientation be changed, meaning form_cam2world[:, :3, 1:3] = -1 is the right way?