Open iariav opened 1 year ago
For nerf-slam, the main outputs are rendered RGB images. For sigma-fusion, the main outputs are 3D meshes. For both approaches, the intermediate outputs are depth maps, depth uncertainties, and 3D poses, which combined can be used to create point clouds.
First, thank you for sharing this awesome work. looks amazing! just trying to understand what is the output of your process - is it a point cloud? a mesh? just a rendered RGB image?
my main interest is getting the best possible 3D model of the scene.
thanks again