search

facebookresearch / robust-dynrf

An algorithm for reconstructing the radiance field of a dynamic scene from a casually-captured video.
MIT License
219 stars 11 forks source link

How is the pose represented using 9 numbers? #23

Open dawood95 opened 11 months ago

dawood95 commented 11 months ago

https://github.com/facebookresearch/robust-dynrf/blob/c56be705940c488cdfeac73d51c332d75101d60c/camera.py#L8

Can you explain how 1x9 is getting converted to 3x4 / the reasoning behind?

aboelela924 commented 11 months ago

the rotation matrix columns are orthogonal to each other so if you take the first two and do a dot product you will get the third column. I am not sure from an optimization point view how much beneficial that is.