We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
Why do you think that https://github.com/isl-org/MiDaS is a good alternative to consistent_depth
We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
Why do you think that https://github.com/isl-org/MiDaS is a good alternative to consistent_depth