Paper materials
- paper/fungraph/3d-gaussian-splatting/3d_gaussian_splatting_low.pdf
- Information website/fungraph/3d-gaussian-splatting/
- GitHub /graphdeco-inria/gaussian-splatting
- Related papers
-
/html/2406.18533v1
On Scaling Up 3D Gaussian Splatting Training
-
/html/2406.18533v1
Extended reading
-
/p/680669616
This article is more detailed and easy to understand - /blog/the-rise-of-3d-gaussian-splatting
- /articles/gaussian-splatting
- Animatable Gaussian Avatar /heawon-yoon/anim-gaussian
Use 3D Gaussian to create 3D character animation avatars, including installation steps
video
Collection/playlist?list=PLAGyKNXhhw2l-OlYOvCxyQ2l29rypwIjW
- 3D Gaussian Splatting for Beginners
- Model data description Understanding the Gaussian splatting model
- 3D NeRF (another implementation) and Gaussian Splatting Real World Applications for NeRFs and Gaussian Splatting - Simulation, Real Estate, Cinema, AR, VR!
- Introduction to 3D NeRF NeRF: Neural Radiance Fields for Beginners
- 3D NeRF and Gaussian Comparison Novel View Rendering and 3D Reconstruction - NeRFs vs Gaussian Splatting
- Installation, Training and Rendering in Linux - Setup, Training and Rendering
other
- Creating 3D Game Models from Video using Photogrammetry /watch?v=bDHJM6nAKtc
3D reconstruction technology 7 years ago - 3D Gaussian Splatting Demo /watch?v=c0VNckM21B0
After shooting with iPhone XR, the effect demonstration of using 3D Gaussian reconstruction
B station Chinese
-
/video/BV11e411n79b
3D Gaussian Introduction -
/video/BV1bJ4m1b7qW/
Comparison of the effects of 3D Gaussian and the other two reconstruction methods
Installation steps
Install the necessary libraries and dependencies
Ubuntu
apt update
apt install build-essential ninja-build
View the graphics card
(base) root@ubuntu22:~# nvidia-smi
Sun Mar 30 17:21:08 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.78 Driver Version: 550.78 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3080 Off | 00000000:00:08.0 Off | N/A |
| 30% 23C P8 8W / 320W | 10MiB / 10240MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 709 G /usr/lib/xorg/Xorg 4MiB |
+-----------------------------------------------------------------------------------------+
Cuda
Install Cuda Toolkit
/cuda-toolkit-archive
View cuda version
nvcc -V
Cuda 12.4
/cuda-12-4-1-download-archive
There is a problem with this installation
wget /compute/cuda/12.4.1/local_installers/cuda_12.4.1_550.54.15_linux.run
sudo sh cuda_12.4.1_550.54.15_linux.run
This installation passes
wget /compute/cuda/repos/ubuntu2204/x86_64/
sudo mv /etc/apt//cuda-repository-pin-600
wget /compute/cuda/12.4.1/local_installers/cuda-repo-ubuntu2204-12-4-local_12.4.1-550.54.15-1_amd64.deb
dpkg -i cuda-repo-ubuntu2204-12-4-local_12.4.1-550.54.15-1_amd64.deb
cp /var/cuda-repo-ubuntu2204-12-4-local/cuda-*- /usr/share/keyrings/
apt update
apt install cuda-toolkit-12-4
Not tried
wget /compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt-get update
sudo apt-get -y install cuda-toolkit-12-4
examine
(base) root@ubuntu22:~/Download# /usr/local/cuda/bin/nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Mar_28_02:18:24_PDT_2024
Cuda compilation tools, release 12.4, V12.4.131
Build cuda_12.4.r12.4/compiler.34097967_0
Cuda 12.1
/cuda-12-1-1-download-archive
Method 1: Using run file, there was an error in compilation
# This file has nearly 4.5GB, and you need to increase bandwidth and plan your time.
wget /compute/cuda/12.1.1/local_installers/cuda_12.1.1_530.30.02_linux.run
sh cuda_12.1.1_530.30.02_linux.runMethod 2: Install the apt deb method, and the last prompts that the version is inconsistent
wget /compute/cuda/repos/ubuntu2204/x86_64/
sudo mv /etc/apt//cuda-repository-pin-600
wget /compute/cuda/12.1.1/local_installers/cuda-repo-ubuntu2204-12-1-local_12.1.1-530.30.02-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2204-12-1-local_12.1.1-530.30.02-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu2204-12-1-local/cuda-*- /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda
Conda
Install Miniconda, Installation Instructions:/milton/p/18023969
Enable conda
eval "$(/home/milton/miniconda3/bin/conda hook)"
Create a conda environment with python version 3.10.12
conda create --name test001 python=3.10.12
conda activate test001
Pytorch
Visit the Pytorch official website/
Starting from 2.6, the conda mode installation is no longer available, and 2.6 only supports 11.8 and 12.4. If you want to use 12.1, you need to replace it with 2.5.
Cuda 12.6 Install Pytorch 2.6
pip3 install torch torchvision torchaudio --index-url /whl/cu126
Cuda 12.4 Install Pytorch 2.6
pip3 install torch torchvision torchaudio
Cuda 12.1 Install Pytorch 2.5.1
Conda
# CUDA 11.8
conda install pytorch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 pytorch-cuda=11.8 -c pytorch -c nvidia
# CUDA 12.1
conda install pytorch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 pytorch-cuda=12.1 -c pytorch -c nvidia
# CUDA 12.4
conda install pytorch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 pytorch-cuda=12.4 -c pytorch -c nvidia
Pip
# CUDA 11.8
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url /whl/cu118
# CUDA 12.1
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url /whl/cu121
# CUDA 12.4
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url /whl/cu124
other
pip install plyfile tqdm tensorboard six
pip install opencv-python
Export the project
Export the project warehouse
git clone /graphdeco-inria/gaussian-splatting --recursive
Install the module
#gaussian
pip install submodules/diff-gaussian-rasterization
pip install submodules/simple-knn
Download training materials
In the projectGitHub repositoryFind the Running section on the home page, and you can find this download link
You can find our SfM data sets for Tanks&Temples and Deep Blending here:
/fungraph/3d-gaussian-splatting/datasets/input/tandt_db.zip
Then there is an output directory If you do not provide an output model directory (-m), trained models are written to folders with randomized unique names inside the output directory. At this point, the trained models may be viewed with the real-time viewer (see further below).
Default dataset test
Training: Use the data that comes with the project
python -s [material path]
# .
python -s ./data/tandt/truckYou can view the GPU situation during execution
(base) root@ubuntu22:~/WorkPython# nvidia-smi
Sun Mar 30 17:59:38 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.78 Driver Version: 550.78 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3080 Off | 00000000:00:08.0 Off | N/A |
| 61% 69C P2 308W / 320W | 5499MiB / 10240MiB | 97% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 709 G /usr/lib/xorg/Xorg 4MiB |
| 0 N/A N/A 7040 C python 5484MiB |
+-----------------------------------------------------------------------------------------+
Rendering:
python -m [training result path]python -m <path to trained model> # Compute error metrics on renderings
Result View
After downloading the model file, view it through this website
/tools/gaussian-splatting
Problem handling
CUDA installation failed
(base) root@ubuntu22:~/Download# sudo sh cuda_12.1.1_530.30.02_linux.run
Installation failed. See log at /var/log/ for details.
(base) root@ubuntu22:~/Download# more /var/log/
(test001) root@ubuntu22:~/Download# more /var/log/
...
Using built-in stream user interface
-> Detected 8 CPUs online; setting concurrency level to 8.
-> Scanning the initramfs with lsinitramfs...
-> Executing: /usr/bin/lsinitramfs -l /boot/-6.5.0-28-generic
-> The file '/tmp/.X0-lock' exists and appears to contain the process ID '737' of a running X server.
-> You appear to be running an X server. Installing the NVIDIA driver while X is running is not recommended, as doing so may prevent the
installer from detecting some potential installation problems, and it may not be possible to start new graphics applications after a new
driver is installed. If you choose to continue installation, it is highly recommended that you reboot your computer after installation
to use the newly installed driver. (Answer: Abort installation)
ERROR: Installation has failed. Please see the file '/var/log/' for details. You may find suggestions on fixing ins
tallation problems in the README available on the Linux driver download page at .
Stop X Server and then install it
systemctl stop display-manager
we could not find ninja or g++
sudo apt-get update
sudo apt install build-essential
sudo apt-get install ninja-build
No such file or directory: ‘:/usr/local/cuda-11.8/bin/nvcc
Execute the command directly on the current command line
export CUDA_HOME=/usr/local/cuda
install again
pip install submodules/diff-gaussian-rasterization
pip install submodules/simple-knn