Metric Pose from the reconstruction

Hello, thanks for this great work ! I wonder how I can get netric pose from the pose estimations if I have a stereo camera and I have a known baseline between the left and right imager ?

Is this possible to add somewhere in the optimization process ?

Hi,

Sorry for the late reply. If you only care about two cameras, left and right, it should be quite easy. You just need to force the relative translation vector between these two cameras as the baseline you have, and do not optimize the translation vector. You can do it by detaching the variables corresponding to translation after this line:

PoseDiffusion/pose_diffusion/util/geometry_guided_sampling.py

Line 84 in 41d1cf8

model_mean.requires_grad_(True)

Thanks ! Is there a way to run this on an input video ? If I give some camera intrinsics as input in a txt file (preferable colmap style)?

Hi yes you can do it although we currently do not have a util function for it. You need to replace the predicted intrinsics manually by your own (note they should be in order). A simple approach may be, first using what we have done in the demo.py to predict camera extri and intri with GGS. Then, with the predicted extri and your provided intri, do another GGS. If you are very confident about your intri, please freeze them during the second GGS optimisation.