WARNING: a fully free version with exhaustive documentation is available on GitHub under this link. Here you can however offer your support by treating me to a coffee :)

Installation

1. Download this repository as a ZIP file
2. Open Blender (3.0.0 or above)
3. In Blender, head to Edit > Preferences > Add-ons, and click Install...
4. Select the downloaded ZIP file, and activate the add-on (Object: BlenderNeRF)

The add-on properties panel is available under 3D View > N panel > BlenderNeRF (the N panel is accessible under the 3D viewport when pressing N).

Setting

BlenderNeRF consists of 3 methods discussed in the sub-sections below. Each method is capable of creating training data and testing data for NeRF in the form of training images and a transforms_train.json respectively transforms_test.json file with the corresponding camera information. The data is archived into a single ZIP file containing training and testing folders. Training data can then be used by a NeRF model to learn the 3D scene representation. Once trained, the model may be evaluated (or tested) on the testing data (camera information only) to obtain novel renders.

Subset of Frames

Subset of Frames (SOF) renders every N frames from a camera animation, and utilises the rendered subset of frames as NeRF training data. The registered testing data spans over all frames of the same camera animation, including training frames. When trained, the NeRF model can render the full camera animation and is consequently well suited for interpolating or rendering large animations of static scenes.

Train and Test Cameras

Train and Test Cameras (TTC) registers training and testing data from two separate user defined cameras. A NeRF model can then be fitted with the data extracted from the training camera, and be evaluated on the testing data.

Camera on Sphere

Camera on Sphere (COS) renders training frames by uniformly sampling random camera views directed at the center from a user controlled sphere. Testing data is extracted from a selected camera.