search

google / dynibar

Implementation of DynIBaR Neural Dynamic Image-Based Rendering (CVPR 2023)
https://dynibar.github.io/
Apache License 2.0
836 stars 42 forks source link

Alleviating the need for Dynamic CVD? #46

Open asafmanor opened 6 months ago

asafmanor commented 6 months ago

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)

asafmanor commented 6 months ago

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

zhengqili commented 4 months ago

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