What dose the parameter "step size ratio " mean? about nerf-loam HOT 3 CLOSED

Another question is about the description in Section4.4 Key-scans selection and refinement

Additionally, to improve the efficiency of the refinement process, only rays or LiDAR points within a truncation distance dt based on the point density are included.

It seems that the final key-scans based optimization only consider the region where the lidar points are dense, and this truncation distance dt has nothing to do with the parameter truncation Tr mentioned before in the paper.
I understand right？

from nerf-loam.

Hi, marrblue.

For sampling, we need sample points inside the voxel. As the voxel size changes, we cannot define a specific sampling step, e.g., sampling points with a 0.1 m gap. So the "step size ratio" is used to define the step size: step_size = step_size_ratio * voxel_size. You can consider "step size" as the sampling gap. If you want to know more about the "step size“, you can refer to Algorithm 1 of the paper Neural Sparse Voxel Fields. This is also the sampling strategy we adopt.

For truncation distance $Tr$: We first define the distance from one point to the nearest plane as SDF value, and the $Tr$ is the maximum SDF value we care about: if $SDF({\bf p}) > Tr$, then $SDF({\bf p}) = Tr$. As for $dt$, it's the maximum distance from LiDAR points to LiDAR. For points with distances bigger than $dt$, we simply discard them. It's as you said: only consider the region where the lidar points are dense.

from nerf-loam.

Hi @JunyuanDeng Thank you for your informative reply and good luck with the early acceptance of the paper : )
I will close this issue.

from nerf-loam.