Visualize 2 avatars in the same scene, just like the introduction page

[9jtiger]

Thank you, for your awesome work!! It's really cool.

Implementing your awesome project, I have few questions....

I want to visualize 2 different avatars in the same scene, just like the introduction page.
However, when I ran the code by following README, only 1 avatar was displayed, in 2 different angles.

Can you give me the code which enables visualizing 2 different avatars in the same scene?

I want to display just like the first photo, but I cannot figure out how to.

[evonneng]

Hi! Sorry for the delay in response. I don't have plans yet to release the script that allows you to render both at the same time since it's a bit messy, but I can describe the process in detail.

1. You will need to render both people/2 avatars and change the render script to reflect this here, where you are getting the render parameters of a person:

   audio2photoreal/sample/generate.py

   Lines 202 to 206 in fee7d12

   	body_renderer.render_full_video(
   	render_data_block,
   	animation_save_path,
   	audio_sr=audio_per_frame * 30,
   	render_gt=args.render_gt,

2. In this function, you will then need to get the correct geometry of both ppl with respect to one another. So you might have to alter the geometry so that they are in the same space.

   audio2photoreal/visualize/render_codes.py

   Line 109 in fee7d12

   default_inputs_copy["lbs_motion"],

3. You will then need to modify this class to update the parameters of rendering, that is including the number of vertices in the mesh, texture, etc. This is a bit tricky, so I can provide a release with the updated code for this part sometime. I will ping when released.

   audio2photoreal/visualize/ca_body/models/mesh_vae_drivable.py

   Line 72 in fee7d12

   class AutoEncoder(nn.Module):

Hope this helps to unblock for now!

[MikeAiJF]

谢谢你的出色工作！真的很酷。

在实施您的出色项目时，我有几个问题……

我想在同一个场景中可视化 2 个不同的头像，就像介绍页面一样。 但是，当我按照 README 运行代码时，只显示了 1 个头像，在 2 个不同的角度。

您能给我提供可以在同一个场景中可视化两个不同化身的代码吗？

我想要像第一张照片那样显示，但我不知道如何做。

Hello, may I ask if you are using the author's dataset or your own dataset