search

google / mannequinchallenge

Inference code and trained models for "Learning the Depths of Moving People by Watching Frozen People."
https://google.github.io/mannequinchallenge
Apache License 2.0
493 stars 104 forks source link

How to get the camera intrinsic parameters from the original YouTube wild videos? #7

Closed luckymingjia closed 5 years ago

luckymingjia commented 5 years ago

I watch that in the dataset, you have supplied the camera intrinsics, but I do not know how do you get them when you create the dataset from the original YouTube ? So could you please explain it for me or tell me what method you have adopted to solve this ? Thank you very much!

fcole commented 5 years ago

Hi, the camera intrinsics are estimated by COLMAP structure-from-motion. We give a bit of explanation if the paper and supplemental material but experimenting with COLMAP is probably required if you haven't used it before.