Rundi Wu

Hi, Image is OK. However, this library can only transfer the skeleton points, not the appearance. In our paper, we further use [this technique](https://arxiv.org/abs/1808.06847) to render the appearance.

Unfortunately I think that one is not public available due to patent restriction, but there are similar repos like [this](https://github.com/carolineec/EverybodyDanceNow) that may satisfies your need.

Hi, thanks for taking interest in our work! We call it performance cloning mainly because we used the method in this work [Deep Video-Based Performance Cloning](https://arxiv.org/abs/1808.06847). I'm not sure is...

Hi Nickson, Thanks for taking interest in our paper. To Q1: We cannot say for sure whether there is a proportional relation. According to our experience, the interpolation results looks...

龙龙有兴趣写的话，搞个PR吧，windows我是真的不熟... BTW，branch区分实验的话，到最后branch太多会不会不太好管理。

Hi Abhinav, Part order denoising is a simple future application that we demonstrated. I sort of lost the code for that experiment now, but it only needs several lines of...

It depends on the data. Since it's trained in a supervised manner, I think it cannot generalize well if using it on other data distribution that is much different from...

If I understand correctly, you are asking to generate only a permutation of the input parts, i.e. a sequence of index. Our model cannot do this, but I think you...

I think it is possible, by combining our framework with Pointer Network. But I'm not sure how it works in practice.

Did you use the pretrained model? How do you get the above voxel outputs?