v0.0.2

ShenhanQian/VHAPv0.0.2Oct 29, 2024by ShenhanQian

AI Summary

This release switches from OpenGL rasterizer to CUDA rasterizer to simplify installation, leveraging nvdiffrast's new support for non-multiple-of-8 resolutions and resolutions over 2048x2048.

Key Highlights

Switched from OpenGL to CUDA rasterizer
Simplified installation process
Support for non-multiple-of-8 resolutions
Support for resolutions over 2048x2048

Breaking Changes

Requires upgrading nvdiffrast and clearing torch_extensions cache

New Features

CUDA rasterizer support
Non-multiple-of-8 resolution support
High resolution support (>2048x2048)

Full Release Notes

Since nvdiffrast now supports non-multiple-of-8 resolutions (https://github.com/NVlabs/nvdiffrast/releases/tag/v0.3.2) and resolutions over 2048x2048 (https://github.com/NVlabs/nvdiffrast/releases/tag/v0.3.3) in CUDA rasterizer, we switch from OpenGL rasterizer to CUDA rasterizer to simplify installation. You need to upgrade nvdiffrast via
  >```shell
  >  pip install nvdiffrast@git+https://github.com/ShenhanQian/nvdiffrast@backface-culling -U
  >  rm -r ~/.cache/torch_extensions/*/nvdiffrast*
>  ```