How to obtain the 3D pose?

Question

How to obtain the 3D pose?

zhangyahu1 opened this issue 4 years ago · comments

Thanks for sharing your nice work!

From your paper, you obtain the 3D pose in the camera coordinate according to the 2D pose in the pixel coordiante and the depth. Could you please give me some details about how to obtain 3D joint locations?

Yahui Zhang commented 4 years ago

Thanks!

Yahui Zhang commented 4 years ago

Thanks!

Jiahao Lin · Answer 1 · Tue Aug 18 2020 18:37:15 GMT+0800 (China Standard Time)

Hi @zhangyahu1

Our framework only estimates the 3D joint location for the root joint. To obtain the full 3D pose, we adopt the same 3D pose estimator as in the ICCV 2019 work by Moon et al. You may refer to the code repo here:
https://github.com/mks0601/3DMPPE_POSENET_RELEASE

Yahui Zhang · Answer 2 · Thu Aug 20 2020 23:45:32 GMT+0800 (China Standard Time)

Hi @jiahaoLjh,

How do you set self.bin_start and self.bin_end for calculating the depth? Dose they depend on the specific dataset?

Jiahao Lin · Answer 3 · Fri Aug 21 2020 11:40:29 GMT+0800 (China Standard Time)

Hi @zhangyahu1,

We set bin_start and bin_end based on the statistics of the dataset to guarantee that the bins range is large enough to cover the depths of all persons in the dataset.