Alleviating the need for Dynamic CVD?

Open asafmanor opened this issue 2 years ago • 2 comments

Hi, Given that I use my own depth predictions, is there a way to create poses_bounds_cvd table without running and training CVD? In particular, how are the 17 parameters constructed?

(Assume I have access the COLMAP outputs)

Dec 26 '23 08:12 asafmanor

Assuming I am creating poses through COLMAP (wrapper from LLFF) And have my own metric depth maps

Dec 27 '23 11:12 asafmanor

Hi, If you have metric depth maps ready, you can align your depth maps with COLMAP pose or vice versa before feeding to Dynibar

Mar 08 '24 18:03 zhengqili