测试输入的2d pose 会生成5个3d假设吗

chaneyddtt / Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network

Code for our CVPR2019 paper: Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network

MIT License

97 stars 9 forks source link

测试输入的2d pose 会生成5个3d假设吗 #9

Open wangxiaobai2268 opened 4 years ago

wangxiaobai2268 commented 4 years ago

小姐姐你好！如果我想拿2d数据输入，没有3d标注,会生成5个假设吗?

chaneyddtt commented 4 years ago

Hi @wangxiaobai2268, You need the 3d label to train the network since our work is fully supervised. After training, the network will generate multiple hypotheses (depends on how many kernels you use during training) for each 2d input.