XiangyuXu

Thanks for your great work! We applied Swin Transformer to video frame interpolation. With good efficiency, the model achieves the state-of-the-art performance on video interpolation on several benchmark datasets, including...

Hi Xiaolong, Thanks for making this great repo for 3D computer vision! Just would like to mention three of our recent works: 1. "3D human pose, shape and texture from...

Hi, Thanks for the great contributions. For the StyleGAN2 backbone, I find this part hard to understand: https://github.com/NVlabs/eg3d/blob/493076071bc400be3289dd6725ef1eef0a552a9d/eg3d/training/networks_stylegan2.py#L499 Shouldn't "self.num_ws += block.num_torgb" happen for every Block? To my understanding, every...

What is the scale net?

3

I notice that there is a scale net in the code. However, I cannot find the corresponding descriptions in the paper. Could you please provide more explanations about this scale...

Thanks for the great work. May I know if one network is trained for all objects or only for one object?