mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-11 02:24:38 +08:00

Alexander Kristoffersen 07a0dbc3a1

Update on Record3D Dataset (small fixes + documentation) (#286 )

* updated dataset to deal with downscale factor and dataset size.

* added docs.

* updated resizing array to always guarantee size of dataset.

2022-08-22 17:15:18 -07:00

1.9 KiB

Raw Blame History

Dataset configuration

Specifying dataset

The dataset path and type is specified in the model config. Both dataset_inputs_train and a dataset_inputs_eval need to be set. You can see configs/graph_default.yaml for more details on what a full config would look like.

data:
  dataset_inputs_train:
    data_directory: data/instant_ngp/fox
    dataset_format: instant_ngp
    downscale_factor: 1
    alpha_color: white
  dataset_inputs_eval:
    data_directory: data/instant_ngp/fox
    dataset_format: instant_ngp
    downscale_factor: 1
    alpha_color: white

Visualize dataset

You can use notebooks/visualize_dataset.ipynb to see how your formatted dataset looks. This code will load a dataset from a yaml config, show the camera poses, and visualize rays with the specified collider in the config. TODO: add a better visualization with images too

Supported datasets

We include support for a set of standard dataset formats.

Blender Synthetic

:color: primary
:outline:
Download

dataset_format: blender

Classic NeRF dataset including the "lego bulldozer" scene that was released with the original NeRF paper.

Instant NGP

:color: primary
:outline:
Download

dataset_format: instant_ngp

MipNeRF 360

:color: primary
:outline:
Download

dataset_format: mipnerf_360

Record3D

:color: primary
:outline:
Download

dataset_format: record_3d

Directly import dataset recorded from a >= iPhone 12 Pro using the Record3D app.

Record a video and export with the EXR + JPG sequence format. Unzip export and rgb folder before training.

1.9 KiB Raw Blame History