/Nerf-Cuda

Primary LanguageC++

Introduction

This project achieves NeRF rendering based on C++, Cuda and some open source packages like tiny-cuda-nn and so on. Generally, it's faster than NeRF implementation based on python.

plan

  • Static scene rendering based on NeRF model
  • Dynamic scene rendering based on some dynamic NeRF model

Building the Library

$ git clone git@github.com:metaverse3d2022/Nerf-Cuda.git 
$ git submodule update --init --recursive
  • Compile
$ mkdir build
$ cd build
$ cmake ..
$ make -j16
$ # In another way, you can just run "source build.sh". After compiling, you can run ./build/testbed for testing.

Usage

$ ./build/render_server # open the render server

Troubleshooting compile errors

Problem Resolution
CMake error: No CUDA toolset found / CUDA_ARCHITECTURES is empty for target "cmTC_0c70f" Windows: the Visual Studio CUDA integration was not installed correctly. Follow these instructions to fix the problem without re-installing CUDA. (#18)
Linux: Environment variables for your CUDA installation are probably incorrectly set. You may work around the issue using cmake . -B build -DCMAKE_CUDA_COMPILER=/usr/local/cuda-<your cuda version>/bin/nvcc (#28)

Reference