You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
What is the best way to estimate the camera trajectory on longer videos (1.5k+ frames)?
Does it make sense to run inference per tuples of images and then accumulate the overall trajectory?
For example, images [0, 1, ... 10], [10, ..., 20]?
Also, does the camera convention follow OpenCV format (X right, Y down, Z forward)?
The text was updated successfully, but these errors were encountered:
Thanks for your work!
What is the best way to estimate the camera trajectory on longer videos (1.5k+ frames)?
Does it make sense to run inference per tuples of images and then accumulate the overall trajectory?
For example, images [0, 1, ... 10], [10, ..., 20]?
Also, does the camera convention follow OpenCV format (X right, Y down, Z forward)?
The text was updated successfully, but these errors were encountered: