about the rasterizer and dense mesh texture

[hxflyer]

congrats, its a great work! Just spend some time installing pytorch3D on Windows, it's really painful, frome user friendly pespective, just FYI, it would be much easier to use nvdiffrast instead pytorch3D, since you already use nvdiffrast in your project, Also, if you have time ,pls consider replace the segment_face from tensorflow to pytorch (since you already use pytorch used in your project) . Those two improvement coulds help others to build applications and futher research projects based on HRN.

BTW, I spend a day to read you code and add the uv data to dense mesh, its also very important for many users.

[ZhenyanSun]

congrats, its a great work! Just spend some time installing pytorch3D on Windows, it's really painful, frome user friendly pespective, just FYI, it would be much easier to use nvdiffrast instead pytorch3D, since you already use nvdiffrast in your project, Also, if you have time ,pls consider replace the segment_face from tensorflow to pytorch (since you already use pytorch used in your project) . Those two improvement coulds help others to build applications and futher research projects based on HRN.

BTW, I spend a day to read you code and add the uv data to dense mesh, its also very important for many users.

thanks for your information. Could you share the changed code?

[youngLBW]

congrats, its a great work! Just spend some time installing pytorch3D on Windows, it's really painful, frome user friendly pespective, just FYI, it would be much easier to use nvdiffrast instead pytorch3D, since you already use nvdiffrast in your project, Also, if you have time ,pls consider replace the segment_face from tensorflow to pytorch (since you already use pytorch used in your project) . Those two improvement coulds help others to build applications and futher research projects based on HRN.

BTW, I spend a day to read you code and add the uv data to dense mesh, its also very important for many users.

Thanks for your sharing! These two problems do bring troubles to the users. We will solve these two problems and add the code for dense mesh texture in the near future.

[475651582]

congrats, its a great work! Just spend some time installing pytorch3D on Windows, it's really painful, frome user friendly pespective, just FYI, it would be much easier to use nvdiffrast instead pytorch3D, since you already use nvdiffrast in your project, Also, if you have time ,pls consider replace the segment_face from tensorflow to pytorch (since you already use pytorch used in your project) . Those two improvement coulds help others to build applications and futher research projects based on HRN.

BTW, I spend a day to read you code and add the uv data to dense mesh, its also very important for many users.

Hi hxflyer, I am also having trouble to generate dense uv data. Could you share the code? Many thanks!