gaussian-splatting

# 3D Gaussian Splatting for Real-Time Radiance Field Rendering Bernhard Kerbl*, Georgios Kopanas*, Thomas Leimkühler, George Drettakis (* indicates equal contribution)
| [Webpage](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/) | [Full Paper](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/3d_gaussian_splatting_high.pdf) | [Video](https://youtu.be/T_kXY43VZnk) | [Other GRAPHDECO Publications](http://www-sop.inria.fr/reves/publis/gdindex.php) | [FUNGRAPH project page](https://fungraph.inria.fr) |
| [T&T+DB COLMAP (650MB)](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/datasets/input/tandt_db.zip) | [Pre-trained Models (14 GB)](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/datasets/pretrained/models.zip) | [Viewers for Windows (60MB)](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/binaries/viewers.zip) | [Evaluation Images (7 GB)](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/evaluation/images.zip) |
This repository contains the official authors implementation associated with the paper "3D Gaussian Splatting for Real-Time Radiance Field Rendering", which can be found [here](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/). We further provide the reference images used to create the error metrics reported in the paper, as well as recently created, pre-trained models. Abstract: *Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (≥ 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.* ## Funding and Acknowledgments This research was funded by the ERC Advanced grant FUNGRAPH No 788065. The authors are grateful to Adobe for generous donations, the OPAL infrastructure from Université Côte d’Azur and for the HPC resources from GENCI–IDRIS (Grant 2022-AD011013409). The authors thank the anonymous reviewers for their valuable feedback, P. Hedman and A. Tewari for proofreading earlier drafts also T. Müller, A. Yu and S. Fridovich-Keil for helping with the comparisons. ## NEW FEATURES ! We have limited resources for maintaining and updating the code. However, we have added a few new features since the original release that are inspired by some of the excellent work many other researchers have been doing on 3DGS. We will be adding other features within the ability of our resources. **Update of October 2024**: We integrated [training speed acceleration](#training-speed-acceleration) and made it compatible with [depth regularization](#depth-regularization), [anti-aliasing](#anti-aliasing) and [exposure compensation](#exposure-compensation). We have enhanced the SIBR real time viewer by correcting bugs and adding features in the [Top View](#sibr-top-view) that allows visualization of input and user cameras. **Update of Spring 2024**: Orange Labs has kindly added [OpenXR support](#openxr-support) for VR viewing. ## Step-by-step Tutorial Jonathan Stephens made a fantastic step-by-step tutorial for setting up Gaussian Splatting on your machine, along with instructions for creating usable datasets from videos. If the instructions below are too dry for you, go ahead and check it out [here](https://www.youtube.com/watch?v=UXtuigy_wYc). ## Colab User [camenduru](https://github.com/camenduru) was kind enough to provide a Colab template that uses this repo's source (status: August 2023!) for quick and easy access to the method. Please check it out [here](https://github.com/camenduru/gaussian-splatting-colab). ## Cloning the Repository The repository contains submodules, thus please check it out with ```shell # SSH git clone [email protected]:graphdeco-inria/gaussian-splatting.git --recursive ``` or ```shell # HTTPS git clone https://github.com/graphdeco-inria/gaussian-splatting --recursive ``` ## Overview The codebase has 4 main components: - A PyTorch-based optimizer to produce a 3D Gaussian model from SfM inputs - A network viewer that allows to connect to and visualize the optimization process - An OpenGL-based real-time viewer to render trained models in real-time. - A script to help you turn your own images into optimization-ready SfM data sets The components have different requirements w.r.t. both hardware and software. They have been tested on Windows 10 and Ubuntu Linux 22.04. Instructions for setting up and running each of them are found in the sections below. ## Optimizer The optimizer uses PyTorch and CUDA extensions in a Python environment to produce trained models. ### Hardware Requirements - CUDA-ready GPU with Compute Capability 7.0+ - 24 GB VRAM (to train to paper evaluation quality) - Please see FAQ for smaller VRAM configurations ### Software Requirements - Conda (recommended for easy setup) - C++ Compiler for PyTorch extensions (we used Visual Studio 2019 for Windows) - CUDA SDK 11 for PyTorch extensions, install *after* Visual Studio (we used 11.8, **known issues with 11.6**) - C++ Compiler and CUDA SDK must be compatible ### Setup #### Local Setup Our default, provided install method is based on Conda package and environment management: ```shell SET DISTUTILS_USE_SDK=1 # Windows only conda env create --file environment.yml conda activate gaussian_splatting ``` Please note that this process assumes that you have CUDA SDK **11** installed, not **12**. For modifications, see below. Tip: Downloading packages and creating a new environment with Conda can require a significant amount of disk space. By default, Conda will use the main system hard drive. You can avoid this by specifying a different package download location and an environment on a different drive: ```shell conda config --add pkgs_dirs / conda env create --file environment.yml --prefix //gaussian_splatting conda activate //gaussian_splatting ``` #### Modifications If you can afford the disk space, we recommend using our environment files for setting up a training environment identical to ours. If you want to make modifications, please note that major version changes might affect the results of our method. However, our (limited) experiments suggest that the codebase works just fine inside a more up-to-date environment (Python 3.8, PyTorch 2.0.0, CUDA 12). Make sure to create an environment where PyTorch and its CUDA runtime version match and the installed CUDA SDK has no major version difference with PyTorch's CUDA version. #### Known Issues Some users experience problems building the submodules on Windows (```cl.exe: File not found``` or similar). Please consider the workaround for this problem from the FAQ. ### Running To run the optimizer, simply use ```shell python train.py -s ``` Command Line Arguments for train.py #### --source_path / -s Path to the source directory containing a COLMAP or Synthetic NeRF data set. #### --model_path / -m Path where the trained model should be stored (```output/``` by default). #### --images / -i Alternative subdirectory for COLMAP images (```images``` by default). #### --eval Add this flag to use a MipNeRF360-style training/test split for evaluation. #### --resolution / -r Specifies resolution of the loaded images before training. If provided ```1, 2, 4``` or ```8```, uses original, 1/2, 1/4 or 1/8 resolution, respectively. For all other values, rescales the width to the given number while maintaining image aspect. **If not set and input image width exceeds 1.6K pixels, inputs are automatically rescaled to this target.** #### --data_device Specifies where to put the source image data, ```cuda``` by default, recommended to use ```cpu``` if training on large/high-resolution dataset, will reduce VRAM consumption, but slightly slow down training. Thanks to [HrsPythonix](https://github.com/HrsPythonix). #### --white_background / -w Add this flag to use white background instead of black (default), e.g., for evaluation of NeRF Synthetic dataset. #### --sh_degree Order of spherical harmonics to be used (no larger than 3). ```3``` by default. #### --convert_SHs_python Flag to make pipeline compute forward and backward of SHs with PyTorch instead of ours. #### --convert_cov3D_python Flag to make pipeline compute forward and backward of the 3D covariance with PyTorch instead of ours. #### --debug Enables debug mode if you experience erros. If the rasterizer fails, a ```dump``` file is created that you may forward to us in an issue so we can take a look. #### --debug_from Debugging is **slow**. You may specify an iteration (starting from 0) after which the above debugging becomes active. #### --iterations Number of total iterations to train for, ```30_000``` by default. #### --ip IP to start GUI server on, ```127.0.0.1``` by default. #### --port Port to use for GUI server, ```6009``` by default. #### --test_iterations Space-separated iterations at which the training script computes L1 and PSNR over test set, ```7000 30000``` by default. #### --save_iterations Space-separated iterations at which the training script saves the Gaussian model, ```7000 30000 ``` by default. #### --checkpoint_iterations Space-separated iterations at which to store a checkpoint for continuing later, saved in the model directory. #### --start_checkpoint Path to a saved checkpoint to continue training from. #### --quiet Flag to omit any text written to standard out pipe. #### --feature_lr Spherical harmonics features learning rate, ```0.0025``` by default. #### --opacity_lr Opacity learning rate, ```0.05``` by default. #### --scaling_lr Scaling learning rate, ```0.005``` by default. #### --rotation_lr Rotation learning rate, ```0.001``` by default. #### --position_lr_max_steps Number of steps (from 0) where position learning rate goes from ```initial``` to ```final```. ```30_000``` by default. #### --position_lr_init Initial 3D position learning rate, ```0.00016``` by default. #### --position_lr_final Final 3D position learning rate, ```0.0000016``` by default. #### --position_lr_delay_mult Position learning rate multiplier (cf. Plenoxels), ```0.01``` by default. #### --densify_from_iter Iteration where densification starts, ```500``` by default. #### --densify_until_iter Iteration where densification stops, ```15_000``` by default. #### --densify_grad_threshold Limit that decides if points should be densified ba