Can you provide some guidance on preparing the custom dataset?

[XJay18]

Hi, basically, you need to:

1. Prepare a dataset with images and camera information;
2. Obtain corresponding pointcloud data from lidar sensors;
3. Preprocess pointcloud data (e.g., denoising and downsampling);
4. Visualize 3D pointcloud along with cameras, and define the foreground region to cover the view frustums;
5. Implement a custom dataparser in NeRFStudio, which reads images, camera information, and pointcloud data.

You may refer to this link, where I uploaded the code for preprocessing Argoverse2.

[Yellowshuohahaha]

@XJay18 Thank you! It is helpful for me!