search

fabro66 / GAST-Net-3DPoseEstimation

A Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video (GAST-Net)
MIT License
312 stars 70 forks source link

about R=rot, t=0 #57

Open LinJinghuidev opened 2 years ago

LinJinghuidev commented 2 years ago

about R=rot, t=0 (rot = np.array([0.14070565, -0.15007018, -0.7552408, 0.62232804], dtype=np.float32)) R and T are parameters that determine the camera Does this mean that when I create a dataset, the position of the camera relative to the 3D control cannot be changed, and only the camera corresponding to the parameter can create test data

LinJinghuidev commented 2 years ago

When I customize the camera simulation data, do my R and t have to change correspondingly? How do I calculate the values?

chunniunai220ml commented 1 year ago

same question, R and T are determined by camera ? can we change ?

RvMe commented 1 year ago

here maybe useful: https://github.com/zh-plus/video-to-pose3D/issues/52#issuecomment-887322458