Giters

QitaoZhao / PoseFormerV2

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Questions about the results of StridedTrans. in Experiment Table 2

wileychan opened this issue · comments

commented

I noticed in Table 2 that StridedTrans.[15] TMM’22 has an MPJPE of 47.5 and MFLOPs of 342.5. This is far from the results reported in the StridedTrans. article. In the StridedTrans. author's article, an input of 81 frames can reach 45.4 MPJPE. The input of 27 frames can reach 46.9MPJPE and only requires 128MFLOPs.
Can you explain why you chose the result 47.5?
Thanks!

Figure 1： Table 2 in your paper.
image

Figure 2: Table in StridedTrans. author's article
image

commented

The authors mentioned in B. Implementation Details that they used a refinement model. To ensure a fair comparison, we re-ran the model without refinement and reported the results we reproduced.

commented

Thanks for your reply, my question has been answered.