2
$\begingroup$

Simple question. Does YOLOv7 pose estimation model output 3D points? ... And, how to get them?

NOTE: I have already run the test.py over custom images (successfully) with the object detection model.

$\endgroup$

3 Answers 3

1
$\begingroup$

I am also seeking 3D pose estimation tool too.

Sadly, output of YOLOv7 is 2D, the x, y and the confidence score, so there is a 3*17=51 length tensor.

There is a guy tried to use 2 cameras and YOLO to do the 3D estimation, you may take a look. https://github.com/SkalskiP/sport

$\endgroup$
1
  • $\begingroup$ I guess, then, that the only AI (apart OpenPose, maybe?) that outputs 3D poses is smpl-x.is.tue.mpg.de (regrettably I am not able to make it work). $\endgroup$ May 23, 2023 at 7:18
1
$\begingroup$

As far as I know, YOLOv7 is for 2D pose estimation for multi-person pose-estimation, where models like MediaPipe does single-person pose-estimation.

For the 3D pose estimation, I am using the "3D-MPPE" model, since the pretrained models are provided. It is a single person 3D Pose Estimation model.

The 3D-MPPE model has 2 inner models: RootNet and PoseNet.

The RootNet estimates the root depth, which is the z-axis value of the target (relative distance from camera to the target). And the 3D-MPPE PoseNet estimates both x and y axis values of each target joints of the person.

Below are links for 3D-MPPE official repos (for both PoseNet and RootNet), and article for actual usage of the 3D-MPPE model:

3D MPPE PoseNet github repo

3D MPPE RootNet github repo

Estimating 3D pose for athlete tracking using 2D videos and Amazon SageMaker Studio

$\endgroup$
0
$\begingroup$

I believe it's 3D since when I investigated the numeric output for each pedestrian I receive 3*17 = 51 length tensor.

$\endgroup$
2
  • $\begingroup$ Thanks but... How to get them? Any clue? $\endgroup$ Apr 9, 2023 at 14:30
  • $\begingroup$ As it’s currently written, your answer is unclear. Please edit to add additional details that will help others understand how this addresses the question asked. You can find more information on how to write good answers in the help center. $\endgroup$
    – Community Bot
    Apr 14, 2023 at 1:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.