search

CVMI-Lab / Point-UV-Diffusion

(ICCV2023) This is the official PyTorch implementation of ICCV2023 paper: Texture Generation on 3D Meshes with Point-UV Diffusion
159 stars 8 forks source link

[F glutil.cpp:332] eglGetDisplay() failed #2

Closed XiangyuSu611 closed 8 months ago

XiangyuSu611 commented 8 months ago

Hi,

Thank you for sharing this great work!

I encountered an issue when running the fine stage using the provided code test.sh while testing the pre-trained model.

image

I have followed your guidance to build the Python runtime environment, and this code is running on a headless remote server with Ubuntu 20.04. Do you have any suggestions on how to solve this problem?

Thank you!

XinYu-Andy commented 8 months ago

Hi,

Thank you for sharing this great work!

I encountered an issue when running the fine stage using the provided code test.sh while testing the pre-trained model.

image

I have followed your guidance to build the Python runtime environment, and this code is running on a headless remote server with Ubuntu 20.04. Do you have any suggestions on how to solve this problem?

Thank you!

This seems to be an issue related to nvdiffrast (https://github.com/NVlabs/nvdiffrast). I suggest first trying cd geometry_tools/nvdiffrast followed by python install .. If that doesn't work, please check their repository for any relevant information.

XiangyuSu611 commented 8 months ago

python install . and change self.ctx = dr.RasterizeContext(device=self.device) to self.ctx = dr.RasterizeCudaContext(device=self.device) in fine_stage/render_diffusion.pywork for me.

This issue will be closed soon.