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

# 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:
```
 git submodule sync --recursive
 git submodule update --init --recursive --force
```

1.2. Create virtual environment

# 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

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

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
```
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:
```
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

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

python main.py fit \
    --viewer \
    ...

It is recommended to use config file configs/blender.yaml when training on blender dataset.

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

# 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

# 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

... 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.

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:

# 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

deform-gs-new.mp4

python main.py fit \
    --config configs/deformable_blender.yaml \
    --data.path ...

2.6. Mip-Splatting

python main.py fit \
    --config configs/mip_splatting_gsplat.yaml \
    --data.path ...

2.7. LightGaussian

Prune & finetune only currently

Train & densify & prune

... 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)

... fit \
    --config configs/light_gaussian/prune_finetune-gsplat.yaml \
    --data.path ... \
    ... \
    --ckpt_path YOUR_CHECKPOINT_PATH

2.8. AbsGS / EfficientGS

... fit \
    --config configs/gsplat-absgrad.yaml \
    --data.path ...

2.9. 2D Gaussian Splatting

Install diff-surfel-rasterization first

pip install git+https://github.com/hbb1/diff-surfel-rasterization.git@3a9357f6a4b80ba319560be7965ed6a88ec951c6

Then start training

... fit \
    --config configs/vanilla_2dgs.yaml \
    --data.path ...

2.10. Segment Any 3D Gaussians

First, train a 3DGS scene using gsplat

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
```
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

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:

├── 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

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
```
python viewer.py outputs/Truck/seganygs
```
SegAnyGS-WebViewer.mp4

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
Train-head-baseline.mp4	Train-head.mp4
	Day-and-Night.mp4

First generate appearance groups (Colmap or PhotoTourism dataset only)

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

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

pip install submodules/mcmc_relocation

Then training

... 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
```
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
```
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
```
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
```
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

object-recognition.mp4

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

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.:

├──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

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

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
Training only currently
Can not combine with other algorithms directly, e.g. with appearance model

Metrics of MipNeRF360 dataset

One batch per GPU, 30K iterations, no other hyperparameters changed.

PSNR
SSIM
LPIPS

Usage

Training

python main.py fit \
    --config configs/distributed.yaml \
    ...

Merge checkpoints

python utils/merge_distributed_ckpts.py outputs/TRAINED_MODEL_DIR

Start viewer

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

python main.py validate \
    --config outputs/lego/config.yaml

On test set

python main.py test \
    --config outputs/lego/config.yaml

On train set

python main.py validate \
    --config outputs/lego/config.yaml \
    --val_train

Save images that rendered during evaluation/test

python main.py <validate or test> \
    --config outputs/lego/config.yaml \
    --save_val

Then you can find the images in outputs/lego/<val or test>.

4. Web Viewer

Transform	Camera Path	Edit
transform.mp4	animation.mp4	edit.mp4

4.1 Basic usage

Also works for graphdeco-inria/gaussian-splatting's ply output

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

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

python viewer.py \
    Deformable-3D-Gaussians/outputs/lego \
    --vanilla_deformable \
    --reorient disable  # change to enable when loading real world scene

hustvl/4DGaussians

python viewer.py \
    4DGaussians/outputs/lego \
    --vanilla_gs4d

hbb1/2d-gaussian-splatting

# 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

python viewer.py \
    SegAnyGAussians/outputs/Truck \
    --vanilla_seganygs

autonomousvision/mip-splatting

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.

reorient-camera-up.mp4

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.

Name		Name	Last commit message	Last commit date
Latest commit History 467 Commits
configs		configs
internal		internal
notebooks		notebooks
submodules		submodules
tests		tests
utils		utils
.gitignore		.gitignore
.gitmodules		.gitmodules
LICENSE.md		LICENSE.md
README.md		README.md
main.py		main.py
render.py		render.py
requirements.txt		requirements.txt
seganygs.py		seganygs.py
viewer.py		viewer.py

License

yzslab/gaussian-splatting-lightning

Folders and files

Latest commit

History

Repository files navigation

Gaussian Splatting PyTorch Lightning Implementation

Known issues

Features

1. Installation

1.1. Clone repository

1.2. Create virtual environment

1.3. Install PyTorch

1.4. Install requirements

1.5. Install optional packages

2. Training

2.1. Basic command

2.2. Some useful options

2.3. Use nerfstudio-project/gsplat

2.4. Multi-GPU training (DDP)

2.5. Deformable 3D Gaussians

2.6. Mip-Splatting

2.7. LightGaussian

2.8. AbsGS / EfficientGS

2.9. 2D Gaussian Splatting

2.10. Segment Any 3D Gaussians

2.11. Reconstruct a large scale scene with the partitioning strategy like VastGaussian

2.12. Appearance Model

2.13. 3DGS-MCMC

2.14. Feature distillation

2.15. In the wild

Introduction

Usage

2.16. New Multiple GPU training strategy

Introduction

Usage

3. Evaluation

Evaluate on validation set

On test set

On train set

Save images that rendered during evaluation/test

4. Web Viewer

4.1 Basic usage

4.2 Load multiple models and enable transform options

4.3 Load model trained by other implementations

5. F.A.Q.

About

Resources

License

Stars

Watchers

Forks

Releases 10

Packages 0

Contributors 2

Languages

Packages