nerfbaselines

nerfbaselines [OPTIONS] COMMAND [ARGS]...

download-dataset

nerfbaselines download-dataset [OPTIONS] DATASET

Options

-o, --output <output>

Arguments

DATASET

Required argument

evaluate

nerfbaselines evaluate [OPTIONS] PREDICTIONS

Options

-o, --output <output>

Required

Arguments

PREDICTIONS

Required argument

export-demo

Export a demo from a trained model. The interactive demo will be a website (index.html) that can be opened in the browser. Only some methods support this feature.

nerfbaselines export-demo [OPTIONS]

Options

--checkpoint <checkpoint>

Required

-o, --output <output>

Required

--data <data>
--train-embedding <train_embedding>

Select the train embedding index to use for the demo.

--set <options>

Set a parameter for demo export.

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

export-mesh

Export a mesh from a trained model. Only some methods support this feature.

nerfbaselines export-mesh [OPTIONS]

Options

--checkpoint <checkpoint>

Required Path to the checkpoint directory. This directory should contain the nb-info.json file.

-o, --output <output>

Required Path to a directory to save the mesh.

-v, --verbose

Enable verbose logging

--data <data>

Path to a dataset to use for exporting the mesh. This is required for some methods.

--set <options>

Set a parameter for mesh export.

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

fix-checkpoint

nerfbaselines fix-checkpoint [OPTIONS]

Options

--checkpoint <checkpoint>

Required

--data <data>

Required

--method <method_name>
--new-checkpoint <new_checkpoint>

Required Path to save the new checkpoint

-v, --verbose
--set <config_overrides>

Override a parameter in the method.

--presets <presets>

Apply a comma-separated list of preset to the method. If no –presets is supplied, or if a special @auto preset is present, the method’s default presets are applied (based on the dataset metadata).

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

fix-output-artifact

nerfbaselines fix-output-artifact [OPTIONS]

Options

--input <input>

Required

--data <data>
--method <method_name>
--rebuild-checkpoint
--rerun-evaluation
--rerun-render
--output <new_artifact>

Path to save the new output artifact

--force
--inplace
--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

generate-dataset-results

nerfbaselines generate-dataset-results [OPTIONS]

Options

--results <results>
--dataset <dataset>
--output-type <output_type>
Options:

markdown | json

Options:

paper | website | results | none

--output <output>

install-method

nerfbaselines install-method [OPTIONS]

Options

--method <method>
Options:

tensorf | zipnerf | instant-ngp | gaussian-opacity-fields | mipnerf360 | tetra-nerf | scaffold-gs | gaussian-splatting | wild-gaussians | colmap | nerfonthego | camp | nerfw-reimpl | 2d-gaussian-splatting | mip-splatting | 3dgs-mcmc | gaussian-splatting-wild | kplanes | seathru-nerf | gsplat | nerf | nerfacto

--spec <spec>
--force

Overwrite existing specs

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

render

nerfbaselines render [OPTIONS]

Options

--checkpoint <checkpoint>

Required

--data <data>

Required

--output <output>

output directory or tar.gz file

--split <split>
--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

render-trajectory

nerfbaselines render-trajectory [OPTIONS]

Options

--checkpoint <checkpoint>

Required

--trajectory <trajectory>

Required

--output <output>

Output a mp4/directory/tar.gz file. Use ‘{output}’ as a placeholder for output name.

--resolution <resolution>

Override the resolution of the output

--output-names <output_names>

Comma separated list of output types (e.g. color,depth,accumulation)

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

shell

nerfbaselines shell [OPTIONS] [COMMAND]...

Options

--method <method>

Required

Options:

tensorf | zipnerf | instant-ngp | gaussian-opacity-fields | mipnerf360 | tetra-nerf | scaffold-gs | gaussian-splatting | wild-gaussians | colmap | nerfonthego | camp | nerfw-reimpl | 2d-gaussian-splatting | mip-splatting | 3dgs-mcmc | gaussian-splatting-wild | kplanes | seathru-nerf | gsplat | nerf | nerfacto

-v, --verbose
--backend <backend_name>
Options:

conda | docker | apptainer | python

Arguments

COMMAND

Optional argument(s)

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

test-method

nerfbaselines test-method [OPTIONS]

Options

--method <method_name>

Required Method to use

Options:

2d-gaussian-splatting | 3dgs-mcmc | camp | colmap | gaussian-opacity-fields | gaussian-splatting | gaussian-splatting-wild | gsplat | instant-ngp | kplanes | mip-splatting | mipnerf360 | nerf | nerfacto | nerfonthego | nerfw-reimpl | scaffold-gs | seathru-nerf | tensorf | tetra-nerf | wild-gaussians | zipnerf

--data <dataset>

Required

-v, --verbose
--full

Run the full method training

--steps <steps>

Number of steps to run (for initial tests, not –full)

--presets <presets>

Apply a comma-separated list of preset to the method. If no –presets is supplied, or if a special @auto preset is present, the method’s default presets are applied (based on the dataset metadata).

--set <config_overrides>

Override a parameter in the method.

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

train

nerfbaselines train [OPTIONS]

Options

--method <method_name>

Required Method to use

Options:

2d-gaussian-splatting | 3dgs-mcmc | camp | colmap | gaussian-opacity-fields | gaussian-splatting | gaussian-splatting-wild | gsplat | instant-ngp | kplanes | mip-splatting | mipnerf360 | nerf | nerfacto | nerfonthego | nerfw-reimpl | scaffold-gs | seathru-nerf | tensorf | tetra-nerf | wild-gaussians | zipnerf

--checkpoint <checkpoint>
--data <data>

Required

--output <output>
--logger <logger>

Logger to use. Defaults to tensorboard.

Options:

none | wandb | tensorboard | wandb,tensorboard

--save-iters <save_iters>

When to save the model

--eval-few-iters <eval_few_iters>

When to evaluate on few images

--eval-all-iters <eval_all_iters>

When to evaluate all images

--disable-output-artifact

Disable producing output artifact containing final model and predictions.

--force-output-artifact

Force producing output artifact containing final model and predictions.

--set <config_overrides>

Override a parameter in the method.

--presets <presets>

Apply a comma-separated list of preset to the method. If no –presets is supplied, or if a special @auto preset is present, the method’s default presets are applied (based on the dataset metadata).

--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

viewer

nerfbaselines viewer [OPTIONS]

Options

--checkpoint <checkpoint>
--data <data>
--port <port>
--backend <backend_name>
Options:

conda | docker | apptainer | python

Environment variables

NERFBASELINES_BACKEND

Provide a default for --backend

web

nerfbaselines web [OPTIONS] COMMAND [ARGS]...

build

nerfbaselines web build [OPTIONS]

Options

--data <data_path>

Path to data directory. If not provided, data is generated from the NerfBaselines repository.

--output <output>

Required Output directory.

--datasets <datasets>

List of comma separated dataset ids to include.

--base-path <base_path>

Base path for the website.

--docs <include_docs>

Whether to include the documentation page for all versions, the latest, or none.

Options:

all | latest | none

dev

nerfbaselines web dev [OPTIONS]

Options

--data <data_path>

Path to data directory. If not provided, data is generated from the NerfBaselines repository.

--datasets <datasets>

List of comma separated dataset ids to include.

--docs <include_docs>

Whether to include the documentation page for all versions, the latest, or none.

Options:

all | latest | none