nerfbaselines

nerfbaselines [OPTIONS] COMMAND [ARGS]...

download-dataset

nerfbaselines download-dataset [OPTIONS] DATASET

Options

-o, --output <output>
-v, --verbose

Arguments

DATASET

Required argument

evaluate

nerfbaselines evaluate [OPTIONS] PREDICTIONS

Options

-o, --output <output>

Required

Arguments

PREDICTIONS

Required argument

export-demo

nerfbaselines export-demo [OPTIONS]

Options

--checkpoint <checkpoint>

Required

-o, --output <output>

Required

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

conda | docker | apptainer | python

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
--backend <backend_name>
Options:

conda | docker | apptainer | python

--set <config_overrides>

Override a parameter in the method.

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

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

conda | docker | apptainer | python

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>

generate-web

nerfbaselines generate-web [OPTIONS]

Options

--source <source>

Path to the source directory containing all the results and checkpoint.

--output <dest>

Required Path to the output directory where the web page will be generated.

--sandbox-node

Use a sandboxed node installation.

--datasets <datasets>

A comma separated list of datasets to process.

-v, --verbose

install-method

nerfbaselines install-method [OPTIONS]

Options

--method <method>
Options:

tetra-nerf:latest | mipnerf360:single-gpu | trips | gaussian-splatting-wild | tensorf | tetra-nerf | mip-splatting:large | nerfonthego | gaussian-splatting:large | nerfacto | camp | wild-gaussians | gaussian-splatting | nerfacto:big | zipnerf | seathru-nerf | gaussian-opacity-fields | nerfacto:huge | nerfw-reimpl | mipnerf360 | kplanes | instant-ngp | mip-splatting | nerf

--spec <spec>
--force

Overwrite existing specs

--backend <backend_name>
Options:

conda | docker | apptainer | python

-v, --verbose

render

nerfbaselines render [OPTIONS]

Options

--checkpoint <checkpoint>

Required

--data <data>

Required

--output <output>

output directory or tar.gz file

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

conda | docker | apptainer | python

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)

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

conda | docker | apptainer | python

shell

nerfbaselines shell [OPTIONS]

Options

--method <method>

Required

Options:

tetra-nerf:latest | mipnerf360:single-gpu | trips | gaussian-splatting-wild | tensorf | tetra-nerf | mip-splatting:large | nerfonthego | gaussian-splatting:large | nerfacto | camp | wild-gaussians | gaussian-splatting | nerfacto:big | zipnerf | seathru-nerf | gaussian-opacity-fields | nerfacto:huge | nerfw-reimpl | mipnerf360 | kplanes | instant-ngp | mip-splatting | nerf

--backend <backend>
Options:

conda | docker | apptainer | python

-v, --verbose

test-method

nerfbaselines test-method [OPTIONS]

Options

--method <method_name>

Required Method to use

Options:

camp | gaussian-opacity-fields | gaussian-splatting | gaussian-splatting-wild | gaussian-splatting:large | instant-ngp | kplanes | mip-splatting | mip-splatting:large | mipnerf360 | mipnerf360:single-gpu | nerf | nerfacto | nerfacto:big | nerfacto:huge | nerfonthego | nerfw-reimpl | seathru-nerf | tensorf | tetra-nerf | tetra-nerf:latest | trips | wild-gaussians | zipnerf

--data <dataset>

Required

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

conda | docker | apptainer | python

--set <config_overrides>

Override a parameter in the method.

--fast

Run only the fast tests

--steps <steps>

Number of steps to run

train

nerfbaselines train [OPTIONS]

Options

--method <method_name>

Required Method to use

Options:

camp | gaussian-opacity-fields | gaussian-splatting | gaussian-splatting-wild | gaussian-splatting:large | instant-ngp | kplanes | mip-splatting | mip-splatting:large | mipnerf360 | mipnerf360:single-gpu | nerf | nerfacto | nerfacto:big | nerfacto:huge | nerfonthego | nerfw-reimpl | seathru-nerf | tensorf | tetra-nerf | tetra-nerf:latest | trips | wild-gaussians | zipnerf

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

Required

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

Logger to use. Defaults to tensorboard.

Options:

none | wandb | tensorboard | wandb,tensorboard

-v, --verbose
--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

--backend <backend_name>
Options:

conda | docker | apptainer | python

--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.

viewer

nerfbaselines viewer [OPTIONS]

Options

--checkpoint <checkpoint>
--data <data>
-v, --verbose
--backend <backend>
Options:

conda | docker | apptainer | python

--port <port>

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.

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.