Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/yzslab/gaussian-splatting-lightning
A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer
https://github.com/yzslab/gaussian-splatting-lightning
Last synced: 3 months ago
JSON representation
A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer
- Host: GitHub
- URL: https://github.com/yzslab/gaussian-splatting-lightning
- Owner: yzslab
- License: other
- Created: 2023-10-06T13:44:06.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-08-03T07:14:32.000Z (3 months ago)
- Last Synced: 2024-08-03T08:28:42.429Z (3 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 23.4 MB
- Stars: 369
- Watchers: 10
- Forks: 30
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
- awesome-3D-gaussian-splatting - gaussian-splatting-lightning - A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer (Open Source Implementations / Framework)
README
# Gaussian Splatting PyTorch Lightning Implementation
* Installation
* Training
* Web Viewer
* Changelog
## Known issues
* ~~Multi-GPU training can only be enabled after densification~~ (Try 2.16. New Multiple GPU training strategy)
## Features
* Multi-GPU/Node training
* Switch between diff-gaussian-rasterization and nerfstudio-project/gsplat
* Multiple dataset types support
* Blender (nerf_synthetic)
* Colmap
* Nerfies
* NSVF (Synthetic only)
* MatrixCity (Prepare your dataset)
* PhotoTourism
* Interactive web viewer
* Load multiple models
* Model transform
* Scene editor
* Video camera path editor
* Video renderer
* Load a large number of images without OOM
* Dynamic object mask
* Derived algorithms
* Deformable Gaussians
* Deformable 3D Gaussians (2.5.)
* 4D Gaussian (4.3.) (Viewer Only)
* Mip-Splatting (2.6.)
* LightGaussian (2.7.)
* AbsGS / EfficientGS (2.8.)
* 2D Gaussian Splatting (2.9.)
* Segment Any 3D Gaussians (2.10.)
* Reconstruct a large scale scene with the partitioning strategy like VastGaussian (see 2.11. below)
* New Appearance Model (2.12.): improve the quality when images have various appearances
* 3D Gaussian Splatting as Markov Chain Monte Carlo (2.13.)
* Feature distillation (2.14.)
* In the wild (2.15.)
* New Multiple GPU training strategy (2.16.)
## 1. Installation
### 1.1. Clone repository
```bash
# clone repository
git clone --recursive https://github.com/yzslab/gaussian-splatting-lightning.git
cd gaussian-splatting-lightning
```
* If you forgot the `--recursive` options, you can run below git commands after cloning:
```bash
git submodule sync --recursive
git submodule update --init --recursive --force
```
### 1.2. Create virtual environment
```bash
# create virtual environment
conda create -yn gspl python=3.9 pip
conda activate gspl
```
### 1.3. Install PyTorch
* Tested on `PyTorch==2.0.1`
* You must install the one match to the version of your nvcc (nvcc --version)
* For CUDA 11.8
```bash
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118
```
### 1.4. Install requirements
```bash
pip install -r requirements.txt
```
### 1.5. Install optional packages
* ffmpeg is required if you want to render video: `sudo apt install -y ffmpeg`
* If you want to use nerfstudio-project/gsplat
```bash
pip install git+https://github.com/yzslab/gsplat.git
```
This command will install my modified version, which is required by LightGaussian and Mip-Splatting. If you do not need them, you can also install vanilla gsplat v0.1.12.
* If you need SegAnyGaussian
* gsplat (see command above)
* `pip install hdbscan scikit-learn==1.3.2 git+https://github.com/facebookresearch/segment-anything.git`
* facebookresearch/pytorch3d
For `torch==2.0.1` and cuda 11.8:
```bash
pip install fvcore iopath
pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py39_cu118_pyt201/download.html
```
* Download ViT-H SAM model, place it to the root dir of this repo.: `wget -O sam_vit_h_4b8939.pth https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth`
## 2. Training
### 2.1. Basic command
```bash
python main.py fit \
--data.path DATASET_PATH \
-n EXPERIMENT_NAME
```
It can detect some dataset type automatically. You can also specify type with option `--data.parser`. Possible values are: `Colmap`, `Blender`, `NSVF`, `Nerfies`, `MatrixCity`, `PhotoTourism`, `SegAnyColmap`, `Feature3DGSColmap`.
[NOTE] By default, only checkpoint files will be produced on training end. If you need ply file in vanilla 3DGS's format (can be loaded by SIBR_viewer or some WebGL/GPU based viewer):
* [Option 1]: Convert checkpoint file to ply: `python utils/ckpt2ply.py TRAINING_OUTPUT_PATH`, e.g.:
* `python utils/ckpt2ply.py outputs/lego`
* `python utils/ckpt2ply.py outputs/lego/checkpoints/epoch=300-step=30000.ckpt`
* [Option 2]: Start training with option: `--model.save_ply true`
### 2.2. Some useful options
* Run training with web viewer
```bash
python main.py fit \
--viewer \
...
```
* It is recommended to use config file `configs/blender.yaml` when training on blender dataset.
```bash
python main.py fit \
--config configs/blender.yaml \
...
```
* With mask (colmap dataset only)
* You may need to undistort mask images too: utils/colmap_undistort_mask.py
```bash
# the requirements of mask
# * must be single channel
# * zero(black) represent the masked pixel (won't be used to supervise learning)
# * the filename of the mask file must be image filename + '.png',
# e.g.: the mask of '001.jpg' is '001.jpg.png'
... fit \
--data.parser Colmap \
--data.parser.mask_dir MASK_DIR_PATH \
...
```
* Use downsampled images (colmap dataset only)
You can use `utils/image_downsample.py` to downsample your images, e.g. 4x downsample: `python utils/image_downsample.py PATH_TO_DIRECTORY_THAT_STORE_IMAGES --factor 4`
```bash
# it will load images from `images_4` directory
... fit \
--data.parser Colmap \
--data.parser.down_sample_factor 4 \
...
```
Rounding mode is specified by `--data.parser.down_sample_rounding_mode`. Available values are `floor`, `round`, `round_half_up`, `ceil`. Default is `round`.
* Load large dataset without OOM
```bash
... fit \
--data.train_max_num_images_to_cache 1024 \
...
```
### 2.3. Use nerfstudio-project/gsplat
Make sure that command `which nvcc` can produce output, or gsplat will be disabled automatically.
```bash
python main.py fit \
--config configs/gsplat.yaml \
...
```
### 2.4. Multi-GPU training (DDP)
[NOTE] Try New Multiple GPU training strategy, which can be enabled during densification.
[NOTE] Multi-GPU training with DDP strategy can only be enabled after densification. You can start a single GPU training at the beginning, and save a checkpoint after densification finishing. Then resume from this checkpoint and enable multi-GPU training.
You will get improved PSNR and SSIM with more GPUs:
```bash
# Single GPU at the beginning
python main.py fit \
--config ... \
--data.path DATASET_PATH \
--model.density.densify_until_iter 15000 \
--max_steps 15000
# Then resume, and enable multi-GPU
python main.py fit \
--config ... \
--trainer configs/ddp.yaml \
--data.path DATASET_PATH \
--max_steps 30000 \
--ckpt_path last # find latest checkpoint automatically, or provide a path to checkpoint file
```
### 2.5. Deformable 3D Gaussians
```bash
python main.py fit \
--config configs/deformable_blender.yaml \
--data.path ...
```
### 2.6. Mip-Splatting
```bash
python main.py fit \
--config configs/mip_splatting_gsplat.yaml \
--data.path ...
```
### 2.7. LightGaussian
* Prune & finetune only currently
* Train & densify & prune
```bash
... fit \
--config configs/light_gaussian/train_densify_prune-gsplat.yaml \
--data.path ...
```
* Prune & finetune (make sure to use the same hparams as the input model used)
```bash
... fit \
--config configs/light_gaussian/prune_finetune-gsplat.yaml \
--data.path ... \
... \
--ckpt_path YOUR_CHECKPOINT_PATH
```
### 2.8. AbsGS / EfficientGS
```bash
... fit \
--config configs/gsplat-absgrad.yaml \
--data.path ...
```
### 2.9. 2D Gaussian Splatting
* Install `diff-surfel-rasterization` first
```bash
pip install git+https://github.com/hbb1/diff-surfel-rasterization.git@3a9357f6a4b80ba319560be7965ed6a88ec951c6
```
* Then start training
```bash
... fit \
--config configs/vanilla_2dgs.yaml \
--data.path ...
```
### 2.10. Segment Any 3D Gaussians
* First, train a 3DGS scene using gsplat
```bash
python main.py fit \
--config configs/gsplat.yaml \
--data.path data/Truck \
-n Truck -v gsplat # trained model will save to `outputs/Truck/gsplat`
```
* Then generate SAM masks and their scales
* Masks
```bash
python utils/get_sam_masks.py data/Truck/images
```
You can specify the path to SAM checkpoint via argument `-c PATH_TO_SAM_CKPT`
* Scales
```bash
python utils/get_sam_mask_scales.py outputs/Truck/gsplat
```
Both the masks and scales will be saved in `data/Truck/semantics`, the structure of `data/Truck` will like this:
```bash
├── images # The images of your dataset
├── 000001.jpg
├── 000002.jpg
...
├── semantic # Generated by `get_sam_masks.py` and `get_sam_mask_scales.py`
├── masks
├── 000001.jpg.pt
├── 000002.jpg.pt
...
└── scales
├── 000001.jpg.pt
├── 000002.jpg.pt
...
├── sparse # colmap sparse database
...
```
* Train SegAnyGS
```bash
python seganygs.py fit \
--config configs/segany_splatting.yaml \
--data.path data/Truck \
--model.initialize_from outputs/Truck/gsplat \
-n Truck -v seganygs # save to `outputs/Truck/seganygs`
```
The value of `--model.initialize_from` is the path to the trained 3DGS model
* Start the web viewer to perform segmentation or cluster
```bash
python viewer.py outputs/Truck/seganygs
```
### 2.11. Reconstruct a large scale scene with the partitioning strategy like VastGaussian
| Baseline | Partitioning |
| --- | --- |
|  |  |
|  |  |
There is no single script to finish the whole pipeline. Please refer to below contents about how to reconstruct a large scale scene.
* Partitioning
* MatrixCity: notebooks/matrix_city_aerial_split.ipynb (Refer to MatrixCity.md about preparing MatrixCity dataset)
* Colmap: notebooks/colmap_aerial_split.ipynb
* Training
* MatrixCity: Included in its partitioning notebook
* Colmap: utils/train_colmap_partitions.py
* Optional LightGaussian pruning
* Pruning: notebooks/partition_light_gaussian_pruning.ipynb
* Finetune after pruning: utils/finetune_partition.py
* Merging: notebooks/merge_partitions.ipynb
### 2.12. Appearance Model
With appearance model, the reconstruction quality can be improved when your images have various appearance, such as different exposure, white balance, contrast and even day and night.
This model assign an extra feature vector $\boldsymbol{\ell}^{(g)}$ to each 3D Gaussian and an appearance embedding vector $\boldsymbol{\ell}^{(a)}$ to each appearance group. Both of them will be used as the input of a lightweight MLP to calculate the color.
$$ \mathbf{C} = f \left ( \boldsymbol{\ell}^{(g)}, \boldsymbol{\ell}^{(a)} \right ) $$
Please refer to internal/renderers/gsplat_appearance_embedding_renderer.py for more details.
| Baseline | New Model |
| --- | --- |
| | |
| | |
* First generate appearance groups (Colmap or PhotoTourism dataset only)
```bash
python utils/generate_image_apperance_groups.py PATH_TO_DATASET_DIR \
--image \
--name appearance_image_dedicated # the name will be used later
```
The images in a group will share a common appearance embedding. The command above will assign each image a group, which means that will not share any appearance embedding between images.
* Then start training
```bash
python main.py fit \
--config configs/appearance_embedding_renderer/view_dependent.yaml \
--data.path PATH_TO_DATASET_DIR \
--data.parser Colmap \
--data.parser.appearance_groups appearance_image_dedicated # value here should be the same as the one provided to `--name` above
```
If you are using PhotoTourism dataset, please replace `--data.parser Colmap` with `--data.parser PhotoTourism`.
### 2.13. 3DGS-MCMC
* Install `submodules/mcmc_relocation` first
```bash
pip install submodules/mcmc_relocation
```
* Then training
```bash
... fit \
--config configs/gsplat-mcmc.yaml \
--model.density.cap_max MAX_NUM_GAUSSIANS \
...
```
`MAX_NUM_GAUSSIANS` is the maximum number of Gaussians that will be used.
Refer to ubc-vision/3dgs-mcmc, internal/density_controllers/mcmc_density_controller.py and internal/metrics/mcmc_metrics.py for more details.
### 2.14. Feature distillation
Click me
This comes from Feature 3DGS. But two stage optimization is adapted here, rather than jointly.
* First, train a model using gsplat (see command above)
* Then extract feature map from your dataset
Theoretically, any feature is distillable. You need to implement your own feature map extractor. Here are instructions about extracting SAM and LSeg features.
* SAM
```bash
python utils/get_sam_embeddings.py data/Truck/images
```
With this command, feature maps will be saved to `data/Truck/semantic/sam_features`, and preview to `data/Truck/semantic/sam_feature_preview`, respectively.
* LSeg: please use ShijieZhou-UCLA/feature-3dgs and follow its instruction to extra LSeg features (do not use this repo's virtual environment for it).
* Then start distillation
* SAM
```bash
python main.py fit \
--config configs/feature_3dgs/sam-speedup.yaml \
--data.path data/Truck \
--data.parser.down_sample_factor 2 \
--model.initialize_from outputs/Truck/gsplat \
-n Truck -v feature_3dgs-sam
```
* LSeg
[NOTE] In order to distill LSeg's high-dimensional features, you may need a GPU equipped with a large memory capacity
```bash
python main.py fit \
--config configs/feature_3dgs/lseg-speedup.yaml \
...
```
`--model.initialize_from` is the path to your trained model.
Since rasterizing high dimension features is slow, `--data.parser.down_sample_factor` is used here to smaller the rendered feature map to speedup distillation.
* After distillation finishing, you can use viewer to visualize the feature map rendered from 3D Gaussians
```bash
python viewer.py outputs/Truck/feature_3dgs
```
CLIP is required if you are using LSeg feature: `pip install git+https://github.com/openai/CLIP.git`
LSeg feature is used in this video.
### 2.15. In the wild
| | | | |
| --- | --- | --- | --- |
|  |  |  |  |
#### Introduction
Based on the Appearance Model (2.12.) above, this model can produce a visibility map for every training view indicating whether a pixel belongs to transient objects or not.
The idea of the visibility map is a bit like Ha-NeRF, but rather than uses positional encoding for pixel coordinates, 2D dense grid encoding is used here in order to accelerate training.
Please refer to Ha-NeRF, `internal/renderers/gsplat_appearance_embedding_visibility_map_renderer.py` and `internal/metrics/visibility_map_metrics.py` for more details.
[NOTE] Though it shows the capability to distinguish the pixels of transient objects, may not be able to remove some artifats/floaters belong to transients. And may also treat under-reconstructed regions as transients.
#### Usage
* tiny-cuda-nn is required
```bash
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
```
* Preparing dataset
Download PhotoTourism dataset from here and split file from the "Additional links" here. The split file should be placed at the same path as the `dense` directory of the PhotoTourism dataset, e.g.:
```bash
├──brandenburg_gate
├── dense # colmap database
├── images
├── ...
├── sparse
...
├── brandenburg.tsv # split file
```
[Optional] 2x downsize the images: `python utils/image_downsample.py data/brandenburg_gate/dense/images --factor 2`
* Start training
```bash
python main.py fit \
--config configs/appearance_embedding_visibility_map_renderer/view_independent-2x_ds.yaml \
--data.path data/brandenburg_gate \
-n brandenburg_gate
```
If you have not downsized images, remember to add a `--data.parser.down_sample_factor 1` to the command above.
* Validation on training set
```bash
python main.py validate \
--save_val \
--val_train \
--config outputs/brandenburg_gate/lightning_logs/version_0/config.yaml # you may need to change this path
```
Then you can find the rendered masks and images in `outputs/brandenburg_gate/val`.
### 2.16. New Multiple GPU training strategy
#### Introduction
This is a bit like a simplified version of Scaling Up 3DGS.
In the implementation here, Gaussians are stored, projected and their colors are calculated in a distributed manner, and each GPU rasterizes a whole image for a different camera. No Pixel-wise Distribution currently.
This strategy works with densification enabled.
[NOTE]
* Not well validated yet, still under development
* Multiple GPUs training only currently
* In order to combine with derived algorithms containing neural networks, you need to manually wrap your networks with DDP, e.g.: internal/renderers/gsplat_distributed_appearance_embedding_renderer.py
Metrics of MipNeRF360 dataset
One batch per GPU, 30K iterations, no other hyperparameters changed.
* PSNR
* SSIM
* LPIPS
#### Usage
* Training
```bash
python main.py fit \
--config configs/distributed.yaml \
...
```
By default, all processes will hold a (redundant) replica of the dataset in memory, which may cause CPU OOM. You can avoid this by adding the option `--data.distributed true`, so that each process loads a different subset of the dataset.
* Merge checkpoints
```bash
python utils/merge_distributed_ckpts.py outputs/TRAINED_MODEL_DIR
```
* Start viewer
```bash
python viewer.py outputs/TRAINED_MODEL_DIR/checkpoints/MERGED_CHECKPOINT_FILE
```
## 3. Evaluation
Per-image metrics will be saved to `TRAINING_OUTPUT/metrics` as a `csv` file.
### Evaluate on validation set
```bash
python main.py validate \
--config outputs/lego/config.yaml
```
### On test set
```bash
python main.py test \
--config outputs/lego/config.yaml
```
### On train set
```bash
python main.py validate \
--config outputs/lego/config.yaml \
--val_train
```
### Save images that rendered during evaluation/test
```bash
python main.py \
--config outputs/lego/config.yaml \
--save_val
```
Then you can find the images in `outputs/lego/`.
## 4. Web Viewer
| Transform | Camera Path | Edit |
| --- | --- | --- |
| | | |
### 4.1 Basic usage
* Also works for graphdeco-inria/gaussian-splatting's ply output
```bash
python viewer.py TRAINING_OUTPUT_PATH
# e.g.:
# python viewer.py outputs/lego/
# python viewer.py outputs/lego/checkpoints/epoch=300-step=30000.ckpt
# python viewer.py outputs/lego/baseline/point_cloud/iteration_30000/point_cloud.ply # only works with VanillaRenderer
```
### 4.2 Load multiple models and enable transform options
```bash
python viewer.py \
outputs/garden \
outputs/lego \
outputs/Synthetic_NSVF/Palace/point_cloud/iteration_30000/point_cloud.ply \
--enable_transform
```
### 4.3 Load model trained by other implementations
[NOTE] The commands in this section only design for third-party outputs
* ingra14m/Deformable-3D-Gaussians
```bash
python viewer.py \
Deformable-3D-Gaussians/outputs/lego \
--vanilla_deformable \
--reorient disable # change to enable when loading real world scene
```
* hustvl/4DGaussians
```bash
python viewer.py \
4DGaussians/outputs/lego \
--vanilla_gs4d
```
* hbb1/2d-gaussian-splatting
```bash
# Install `diff-surfel-rasterization` first
pip install git+https://github.com/hbb1/diff-surfel-rasterization.git@28c928a36ea19407cd9754d068bd9a9535216979
# Then start viewer
python viewer.py \
2d-gaussian-splatting/outputs/Truck \
--vanilla_gs2d
```
* Jumpat/SegAnyGAussians
```bash
python viewer.py \
SegAnyGAussians/outputs/Truck \
--vanilla_seganygs
```
* autonomousvision/mip-splatting
```bash
python viewer.py \
mip-splatting/outputs/bicycle \
--vanilla_mip
```
## 5. F.A.Q.
Q: The viewer shows my scene in unexpected orientation, how to rotate the camera, like the `U` and `O` key in the SIBR_viewer?
A: Check the `Orientation Control` on the right panel, rotate the camera frustum in the scene to the orientation you want, then click `Apply Up Direction`.
Besides: You can also click the 'Reset up direction' button. Then the viewer will use your current orientation as the reference.
* First use mouse to rotate your camera to the orientation you want
* Then click the 'Reset up direction' button
##
Q: The web viewer is slow (or low fps, far from real-time).
A: This is expected because of the overhead of the image transfer over network. You can get around 10fps in 1080P resolution, which is enough for you to view the reconstruction quality.