CAMMA-public / SelfPose3d

Official code for "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation"

CAMMA-public/SelfPose3d Issues

Unclear instruction on how to apply this framework to a new dataset. (e.g. get 2d / 3d pseudo poses)
Updated a month ago1
Backbone training: Unclear requirements
Updated 5 months ago4
README not reproducable: CMU Panoptic dataset image extraction missing
Updated 5 months ago2
About the results of 'mvpose' on Panoptic dataset
Updated 5 months ago
README setup not reproducable (missing multi_person_posenet)
Closed 6 months ago2
Missing links for the pretrained backbone model and the the pseudo 2d labels
Closed 6 months ago2