mks0601 / I2L-MeshNet_RELEASE

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Camera coordinates

bavasilev opened this issue · comments

Hello!
The distance from the mesh is estimated by RootNet, but how to get the rotation of the camera used in the visualization of the mesh?
Looking forward to getting any kind of advice.

The global rotation is estimated by I2L-MeshNet.

Could you please pinpoint the place in the code where I can get it from? I was trying to figure it out on my own but failed to do so, as I'm not sure what format it is presented in.

In the lixel stage, I2L-MeshNet predicts in (x,y pixel, z depth) space mesh vertices, so no global rotation is required.
In the param stage, see here:

pose = tgm.rotation_matrix_to_angle_axis(pose).reshape(batch_size,-1)

Thanks a lot!