# New surface model generation method: SurfaceNets

**URL:** https://discourse.slicer.org/t/new-surface-model-generation-method-surfacenets/32430
**Category:** Support
**Tags:** feature
**Created:** [October 26, 2023, 6:20pm UTC](https://discourse.slicer.org/t/new-surface-model-generation-method-surfacenets/32430 "2023-10-26T18:20:50Z")
**Posts on this page:** 1
**Showing post:** 2

<div class="post-metadata">

### Author: ![chir.set](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/chir.set/32/66982_2.png) [@chir.set](https://discourse.slicer.org/u/chir.set)
#### Post date: [November 25, 2023, 8:28pm UTC](https://discourse.slicer.org/t/new-surface-model-generation-method-surfacenets/32430/2 "2023-11-25T20:28:00Z")

</div>

Hi,

I explored a little the new ‘Surface nets’ surface smoothing and made a side-by-side comparison as below with a tubular segment.

Globally, from the default algorithm to the ‘Fast’ and ‘Faster’ ones, it seems that shading and smoothing both decrease in that direction. With high smoothing factor, the difference tends to decrease, at least visually. The speed gain is of course of interest for huge segments.

The whole project can be downloaded [here](https://disk.yandex.com/d/y7rfv1y2_EE9aA).

The image below is posted for immediate reference. It uses a cropped isovoxel sample at 0.3 mm spacing (from CTA-cardio).

From left to right: default algorithm, ‘Fast’ and ‘Faster’  
From top to bottom: 0% smoothing factor, 10%,…,90%, 100%

Regards.

 ![SurfaceSmoothing_3x11](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/e/7/e745359c1adfd57adaabd97d75416ee5800b44dc.jpeg)

---

_[View the full topic](https://discourse.slicer.org/t/new-surface-model-generation-method-surfacenets/32430)._