how to get the Depth、Interial、Skeleton when trianing the new person ? (MHAD)

nihaomiao / CVPR23_LFDM

The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"

BSD 2-Clause "Simplified" License

443 stars 42 forks source link

Closed chenbolin-master closed 1 year ago

chenbolin-master commented 1 year ago

how to get the Depth、Interial、Skeleton when trianing the new person ? (MHAD) @nihaomiao

nihaomiao commented 1 year ago

MHAD uses the RGB-D camera to capture them. You may need to use the RGB-D camera or some pre-trained models to get these extra modalities.