MeisterRender

Repo Introduction

A general-purpose rendering framework for embodied intelligence simulation, aiming to bridge the Sim-to-Real visual gap.

Features

• High-fidelity mesh path-tracing rendering based on Blender-Cycles
• Mesh rasterization and ray tracing rendering based on Blender-EEVEE
• Gaussian Splatting rendering based on our optimized 3DGS and TCGS rasterizers
• Hybrid rendering that combines any kind of mesh renderer and Gaussians renderer

Installation Guide

We recommend using Conda to manage your environment.

conda create -n MeisterRender python==3.11
conda activate MeisterRender
pip install -r requirements.txt

Optional: Set up the Gaussians rendering environment

pip install torch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 --index-url https://download.pytorch.org/whl/cu118

# Option 1: Our optimized GS rasterizers
git clone https://github.com/InternLandMark/OptGaussianRasterization.git --recursive
pip install OptGaussianRasterization/

# Option 2: TCGS rasterizers
git clone https://github.com/DeepLink-org/3DGSTensorCore.git --recursive
pip install 3DGSTensorCore/submodules/tcgs_speedy_rasterizer

Usage Instructions

Download the additional asset package and extract it into the assets directory.

https://drive.google.com/file/d/1inAAXfhhIfnHUoi8Eg_mQ5t-ovRmi1ex/view?usp=sharing

Path Tracing Rendering

python example_pathtracing.py

3DGS Rendering

python example_3dgs.py