Yuliang Xiu
Yuliang Xiu
Try to use PyOpenGL with a higher version, ours is 3.1.5.
I tested demo using GCC 5.4.0, you can firstly try to downgrade the GCC version and then reinstall the ImplicitSegCUDA. Moreover, current ImplicitSegCUDA only supports pytorch==1.4.0, compile it with 1.5...
@Caenorst @caiyongqi Any update on this issue?
No guarantee, but any pull requests are welcome.
Have you installed EGL and set `egl=True` as [dataset.md](https://github.com/YuliangXiu/ICON/blob/master/docs/dataset.md)?
Please `git pull` the latest version, you don't need to uncomment these lines for training.
This issue has never occurred to me, but I found a [related issue](https://github.com/facebookresearch/pytorch3d/issues/1064) in PyTorch3D, maybe it is helpful for you.
@Tessantess, please check [here](https://github.com/YuliangXiu/ICON/blob/master/docs/dataset.md), I corrected some bugs and for now the rendering works well.
> Hope to export out fbx You can refer to [simplify_loc2rot](https://github.com/webaverse/motion-diffusion-model/blob/main/visualize/simplify_loc2rot.py) and [fbx_output](https://github.com/webaverse/motion-diffusion-model/blob/5e57d976e917c34b15c8d7055ae4257cb73e37d7/fbx_output.py#L241) for FBX export.
> Hello M.r. Thank you for nice work! do you have plan to release your rendered RGBD images? You can check this pull request (https://github.com/ytrock/THuman2.0-Dataset/pull/13) for the rendering purpose.