Some questions about the synthesized animation

[hemath1001]

Hi there!
Thanks for your excellent work!
When I use the pretrained model to get synthesized Salsa-Dancing-6, and import synthesized bvh to blender, I find something a little weird and I would be grateful if you could tell me they are correct or bugs?

1. The last joints of hands and feet seem tilted outward.
2. Fingers are missing.
3. One joint of head is missing.

Here is gif. The left one is the original one, ane the middle is the synthesized result without contact fixed, the right one is the synthesized result with contact fixed.

And I'm confused about gt_ and rec_ bvh file in results, they stand for...?

Thanks again for your reply! Wish you all the best :-D

[PeizhuoLi]

Hi, thanks for your question. For your first question, this is because the End Site section in bvh files is discarded by our bvh parser. It does not affect the animation after skinning.

For the missing joints, it's because in our demo we use only the corps joints in Mixamo skeletons, specified here. Since our code is designed to be flexible with skeletal structure, feel free to add the finger joints to the list if you need them.

The gt_* and rec_* stand for ground-truth (the training sequence) and the reconstructed result in different temporal resolution.

Hope this is helpful.

[hemath1001]

Hi, thanks for your question. For your first question, this is because the End Site section in bvh files is discarded by our bvh parser. It does not affect the animation after skinning.

For the missing joints, it's because in our demo we use only the corps joints in Mixamo skeletons, specified here. Since our code is designed to be flexible with skeletal structure, feel free to add the finger joints to the list if you need them.

The gt_* and rec_* stand for ground-truth (the training sequence) and the reconstructed result in different temporal resolution.

Hope this is helpful.

I get it. Thanks a million! <3