search

Shimingyi / MotioNet

A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]
https://rubbly.cn/publications/motioNet/
BSD 2-Clause "Simplified" License
554 stars 82 forks source link

Blender visualization issue. #43

Closed lakpa-tamang9 closed 2 years ago

lakpa-tamang9 commented 2 years ago

I tried to visualize the bvh files using blender. The resulting animation is upside down. Any solution? The initial T-pose is correct but after the second frame the video orientation becomes upside down.

image
Shimingyi commented 2 years ago

Hi @lakpa-tamang9 , for avoiding the camera view ambiguity(different poses on different cameras will yield the same 2d projection), the predicted human motion is always in camera space, which means you should rotate it manually. You can find more explanation in Martinez's paper [1], which provides a baseline to this kind of joint position-based prediction.

20220316142606
  1. Martinez, Julieta, et al. "A simple yet effective baseline for 3d human pose estimation." Proceedings of the IEEE international conference on computer vision. 2017.