Junjie Wang
Junjie Wang
@cdcseacave could you please tell me how to generate such one animation? Are you using built-in tools in meshlab?
这个也太难了，这种姿势和遮挡都是待解决的问题 发自我的小米手机在 polo1968 ***@***.***>，2022年4月6日 下午3:09写道： 感谢您提供的ROMP方法！我尝试使用提供的方法，效果很棒！但是在某些场景下出现了人体无法识别的情况。如图中，红色箭头所指被试者在进行大幅前屈动作时。 由于我不是计算机相关专业的，所以想请问一下，这是什么原因呢？是否有解决方法？ —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>...
the problem seems to stem from old and mismatch version of fastapi (against gradio==4.11.0 and pydantic==2.5.2) `pip install -U fastapi pydantic` works well for me
It seems that your modified version does not support SMPL forward kinematics, it stills uses puppet model as vanilla arcsim, right?
Agreed! It would be really exciting if blendshapes could be estimated and aligned with input audio clip. I am currently working on a pipeline: `user voice->speech recognition->chatgpt->text to speech->blendshapes`. There...