After installation, you will find the settings on the right side in the "N" panel. First, select an output directory and create a bounding box. Then, generate a camera set by clicking either "Create Camera Hemisphere / Central Object" or "Create Camera Large Scene / Indoor". Next, create a point cloud using "Create and Export Point Cloud" and prepare the scene for rendering with "Prepare Render Settings". Finally, render the camera frames as an animation in Blender and export the camera alignments with "Export Camera Files". Now, you can use the output directory—containing the files points3d.ply, transforms_train.json, and transforms_test.json—as input for many NeRF and Gaussian Splatting frameworks.

There is just one final step: you need to start the training process using your preferred framework. We recommend using Postshot, 3DGS or 2DGS. The command to run the training typically looks like: python train.py -s PATH/TO/THE/GENERATED/FOLDER For more information on setting up a Gaussian Splatting framework, refer to this guide: https://github.com/graphdeco-inria/gaussian-splatting.

Please keep in mind that our add-on generates all the necessary files to train a Splat or NeRF of your scene, but you will need to start the training yourself.

You can only use the commercial version for commercial projects. The free version is intended for private use and research purposes.

Check the documentation page for a full explanation of the settings.

Depending on the scene that can happen. Most likely you have many objects or particle systems. Try to decrease the amount of particles converted to meshes. Decreasing the amount of particles can help as well.

Go to "Edit - Preferences - Addons" and in the top right corner hit "install from file". Navigate to the .zip and install.