UniqAI/gaussian-splatting
1
0
Fork 0
mirror of https://github.com/graphdeco-inria/gaussian-splatting synced 2024-11-22 16:28:32 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Added dataset paths

Browse Source
This commit is contained in:
bkerbl 2023-07-04 17:48:37 +02:00
parent 2850f2b235
commit 1746f0fdbe
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@ -1,6 +1,9 @@
# 3D Gaussian Splatting for Real-Time Radiance Field Rendering # 3D Gaussian Splatting for Real-Time Radiance Field Rendering
Bernhard Kerbl*, Georgios Kopanas*, Thomas Leimkühler, George Drettakis (* indicates equal contribution)<br> Bernhard Kerbl*, Georgios Kopanas*, Thomas Leimkühler, George Drettakis (* indicates equal contribution)<br>
| [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) | [Datasets (TODO)](TODO) | [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) | <br> | [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)
[Input Datasets](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/datasets/input/tandt+db.zip) | [Pre-trained Models TODO](TODO)| [Evaluation Renderings TODO](TODO)| <br>
![Teaser image](assets/teaser.png) ![Teaser image](assets/teaser.png)
This repository contains the code 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. This repository contains the code 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.
@ -97,9 +100,7 @@ To run the optimizer, simply use
python train.py -s <path to dataset> python train.py -s <path to dataset>
``` ```
TODO update link The MipNeRF360 scenes are hosted by the paper authors [here](https://jonbarron.info/mipnerf360/). You can find our SfM data sets for Tanks&Temples and Deep Blending [here](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/datasets/input/tandt+db.zip). 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).
You can find our SfM data sets for Tanks&Temples and Deep Blending here. 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).
### Evaluation ### Evaluation
By default, the trained models use all available images in the dataset. To train them while withholding a test set for evaluation, use the ```--eval``` flag. This way, you can render training/test sets and produce error metrics as follows: By default, the trained models use all available images in the dataset. To train them while withholding a test set for evaluation, use the ```--eval``` flag. This way, you can render training/test sets and produce error metrics as follows:
@ -205,7 +206,7 @@ python convert.py -s <location> [--resize] #If not resizing, ImageMagick is not
``` ```
Alternatively, you can use the optional parameters ```--colmap_executable``` and ```--magick_executable``` to point to the respective paths. Please not that on Windows, the executable should point to the COLMAP ```.bat``` file that takes care of setting the execution environment. Once done, ```<location>``` will contain the expected COLMAP data set structure with undistorted, differently sized input images, in addition to your original images and temporary data in the directory ```distorted```. Alternatively, you can use the optional parameters ```--colmap_executable``` and ```--magick_executable``` to point to the respective paths. Please not that on Windows, the executable should point to the COLMAP ```.bat``` file that takes care of setting the execution environment. Once done, ```<location>``` will contain the expected COLMAP data set structure with undistorted, differently sized input images, in addition to your original images and temporary data in the directory ```distorted```.
## FAQ ## FAQ
- *Where do I get data sets, e.g., those referenced in ```full_eval.py```?* The MipNeRF360 data set is provided by the authors of the original paper on the project site. Note that two of the data sets cannot be openly shared and require you to consult the authors directly. For Tanks&Temples and Deep Blending, please use the download links provided above. - *Where do I get data sets, e.g., those referenced in ```full_eval.py```?* The MipNeRF360 data set is provided by the authors of the original paper on the project site. Note that two of the data sets cannot be openly shared and require you to consult the authors directly. For Tanks&Temples and Deep Blending, please use the download links provided at the top of the page.
- *24 GB of VRAM for training is a lot! Can't we do it with less?* Yes, most likely. By our calculations it should be possible with **way** less memory (~8GB). If we can find the time we will try to achieve this. If some PyTorch veteran out there wants to tackle this, we look forward to your pull request! - *24 GB of VRAM for training is a lot! Can't we do it with less?* Yes, most likely. By our calculations it should be possible with **way** less memory (~8GB). If we can find the time we will try to achieve this. If some PyTorch veteran out there wants to tackle this, we look forward to your pull request!