EasyMocap
EasyMocap copied to clipboard
Some data are missing in the Mirrored-Human dataset
I find that the provided mirrored-human dataset is incompleted, the some of the videos and frame annotations are missing, how can I get them?
Which part do you mean?
First, the number of video urls in the 'mirrored-human.json' is 270, but in the 'mirrored-human-base.zip', there are only 204 clips. Moreover, just using the name like 'raw_***', I can not align the clip annotations with the video urls and clips Second, the annotation of each frame is not provided. For example, in the clip of 'raw_000', I can only get smpl and keypoints3d annotations every 50 frames. Maybe I have made some mistakes, it's very nice of you for giving me an answer! Thank you
Hello, the mirrored-human-base.zip
is the sampled frames which are used to train the mentioned network. If you want to get the annotation of each frame, you can just run our provided code.