search

baegwangbin / IronDepth

[BMVC 2022] IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty
MIT License
176 stars 9 forks source link

Would it be possible to get the camera pose of the NYU dataset? #1

Open Rock-100 opened 1 year ago

Rock-100 commented 1 year ago

I am trying to do TSDF-fusion on the NYU dataset using this depth estimation result. But I didn't find the camera pose. Could u tell me how to get the camera pose on the NYU dataset?

Thanks!

baegwangbin commented 1 year ago

Hi, I am sorry for the delayed reply. NYU dataset does not provide camera poses, unfortunately. You can use open-source structure-from-motion packages like COLMAP and OpenSfM to get the camera pose yourselves.