search

ToniRV / NeRF-SLAM

NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields. https://arxiv.org/abs/2210.13641 + Sigma-Fusion: Probabilistic Volumetric Fusion for Dense Monocular SLAM https://arxiv.org/abs/2210.01276
BSD 2-Clause "Simplified" License
1.17k stars 141 forks source link

What is the output type #16

Open iariav opened 1 year ago

iariav commented 1 year ago

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

ToniRV commented 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.