FreeMan_API

FreeMan_API copied to clipboard

Annotations / confidence

3

Thanks for the dataset again. When visualizing the data, I noticed that many labels are incorrect, probably the triangulation or camera calibration failed. Is there any way to obtain some...

isarandi

World Coordinates to Camera Coordinates

1

Hi, @wangjiongw I have read the paper and found out 3d keypoints are world coordinates. I wanted to make FreeMan 3d keypoints(world coordinates) to be matched same as in H36M...

sung-sidewalk

Camera distortion parameters

2

Thanks for this dataset! I'm wondering if I'm using the camera parameters wrong because if I interpret them as the usual 5 distortion parameters as in OpenCV, I get bad...

isarandi

Dataset Structure is different..

4

Hello, I have downloaded dataset via OpenXLab. However, the data structure was not equal to what you've mentioned in readme file. Also, when I checked video fps, it was 25....

sung-sidewalk

Will the pre-trained monocular 3D pose model on Freeman be released？

1

Thanks for your work. I would like to test the generalization of the monocular 3D pose model trained on the Freeman dataset, will the pre-trained model be released? thanks

guoguangchao