what is the difference for data with and without "occ"?

[Wuchuq]

Thank you for your work! For the pre-processed data with name "occ" and without, what's the difference of them?

[hongsukchoi]

As written in the implementation detail (Section 4 of the paper),
we followed "How robust is 3d human pose estimation
to occlusion?".

It is occluding images with PASCAL objects in a random way.

[QitaoZhao]

I have a similar question. What is the difference between the data with "tight" and without for Human3.6m. Thanks for answering.

[Wuchuq]

thank you for your response!

[hongsukchoi]

@QitaoZhao

It’s the tightness of bounding boxes used for training. We preprocessed another version to compare with SPIN setting that used tight bboxes