search

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
MIT License
708 stars 130 forks source link

Can you provide the inference code for the video? #46

Closed OOF-dura closed 3 years ago

OOF-dura commented 3 years ago

Can you provide the inference code for the video? Like those showing in the demo : image

May I know the sources of the three videos?

mks0601 commented 3 years ago

You can apply the demo codes on each frame.

OOF-dura commented 3 years ago

You can apply the demo codes on each frame.

May I know the sources of the three videos?

OOF-dura commented 3 years ago

You can apply the demo codes on each frame.

Sounds like this will cause some jitters.

mks0601 commented 3 years ago

Source: https://virtualhumans.mpi-inf.mpg.de/3DPW/ The video results are obtained by applying my method on each frame.