How to see the 3D reconstruction results (e.g. multi-view images)

Open JuewenPeng opened this issue 9 months ago • 5 comments

Mar 26 '25 04:03 JuewenPeng

Currently supports exporting mesh , see https://github.com/aigc3d/LHM#-inference-pipeline.

Mar 26 '25 06:03 liphao99

As we do not add any hard supervision in the canonical space, the 3D avatar model in the canonical space may have a small probability of having slight artifacts on T-posed space.

Mar 26 '25 06:03 lingtengqiu

I found this code can only export the T-pose mesh. Is it possible to obtain the result under the pose of the reference image?

Mar 26 '25 09:03 JuewenPeng

I will update the interface to export gaussian model under target-view pose.

Mar 27 '25 02:03 lingtengqiu

I will update the interface to export gaussian model under target-view pose.

I would like to ask if it is now possible to get a 3DGS body in the target pose?

Jul 04 '25 14:07 QinglinZhan