May I ask a question? When doing this cross dataset experiment, is the 2D GT coordinates in the 3dhp dataset as the input or the coordinates estimated by the 2D pose estimator hrnet as the input.
I just use 2D GT annots of 3dhp dataset as the 2d input, and the results are as below.
(The 2Dto3D model is trained on this config: stage 2 block 3 evolve: generation_6)
And then I use 2D HRNet outputs as the 2d input, and the results are as below. (The 2d model is final_state.pth you mentioned here. https://github.com/Nicholasli1995/EvoSkeleton/blob/master/docs/2DHPE.md)
May I ask a question? When doing this cross dataset experiment, is the 2D GT coordinates in the 3dhp dataset as the input or the coordinates estimated by the 2D pose estimator hrnet as the input.![image](https://user-images.githubusercontent.com/56756106/182596583-f4835439-a777-4e2f-b3b1-fa1b2653917b.png)
I just use 2D GT annots of 3dhp dataset as the 2d input, and the results are as below. (The 2Dto3D model is trained on this config: stage 2 block 3 evolve: generation_6)
And then I use 2D HRNet outputs as the 2d input, and the results are as below. (The 2d model is final_state.pth you mentioned here. https://github.com/Nicholasli1995/EvoSkeleton/blob/master/docs/2DHPE.md)
![image](https://user-images.githubusercontent.com/56756106/182598715-c9a6c9c4-beb4-487d-822c-452052058a2d.png)