rgbd-pose3d icon indicating copy to clipboard operation
rgbd-pose3d copied to clipboard

Published 20 hours ago • verified publisher icon lmb-freiburg

What are the inputs to VoxelPoseNet during training?

Open cherryjm opened this issue 5 years ago • 0 comments

Hi, thank you for your work! I wonder how to train VoxelPoseNet? The inputs to it are 2D groundtruth? or 2D results predicted by 2D network? And is it possible to cascade 2D and 3D network making it an end-to-end network?

cherryjm avatar Feb 19 '20 14:02 cherryjm