> For the complete documentation index, see [llms.txt](https://docs.phoenixlidar.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.phoenixlidar.com/spatialexplorer-8-and-9/user-interface/toolbars/analytics/create/cloudclean.md).

# CloudClean

**CloudClean** is used to make a smart-decimated cloud, or to increase the precision on surfaces. Smart decimation refers to reducing the density of a pointcloud by removing points furthest from estimated surfaces in the cloud. 

{% hint style="warning" %}
Users have several options for improving precision on hard surfaces. CloudClean decimated will attempt to improve precision without reducing density, similar to [Statistical Outlier Removal](/spatialexplorer-8-and-9/user-interface/toolbars/analytics/classify/classify-statistical-outliers.md) (SOR). The primary difference between the two tools is that SOR will result in a changed classification (assigning points to noise class), whereas CloudClean will create an entirely new pointcloud. For a more arbitrary form of decimation, configure the[ lidar processing settings](/spatialexplorer-8-and-9/user-interface/windows/project/rover/lidars/lidar-processing-settings.md) to exclude every other line, or as is the case with multi-laser systems, utilize auto-downsampling. 
{% endhint %}

<figure><img src="/files/fLnkO8j15txRDfdL6sX7" alt=""><figcaption></figcaption></figure>

**Output Mode:**  Choose between created *Decimated*, *Projected*, or both clouds

**Points per Square Meter:** Target point density for the output cloud. Used only with *Decimated* mode.

**Uniformity:** A value of 1 will try to maximize uniform density in the pointcloud. A value of 0 will disregard uniformity and focus only on improving surface precision. Most users will want to use the default value of 0.&#x20;

### Output Mode:

**Decimated:** Given point density, algorithm picks points that are nearest to the computed surface. It then keeps original points from the cloud, but discards the points furthest away from computed surface.

![Profile Cross Section: Original pointcloud (Red) Vs Decimated pointcloud(Green)](/files/N8TFgpNhcGYJIRqVGRjc)

**Projected:** Projects every original point to a computed surface. It keeps all the points from the cloud, but moves or 'projects' them closer to the computed surface.

![Profile Cross Section: Original pointcloud (Red) Vs Projected pointcloud (Blue)](/files/Bwydq07kGLgLRIgPyZG9)