Skip to content
Neurones 3D Download

Documentation · version 0.34.2

Getting started with Neurones 3D

Neurones 3D (N3D) is point cloud processing software for Windows. This page covers installing it, entering a licence, the interface and the usual order of work. After it, one guide per process, each with the real menu path, numbered steps, the number it was measured at, the command-line equivalent and its limits.

Install

There is no installer. Download the free build, unzip it, and run n3d.exe. It is one self-contained executable for 64-bit Windows 10 and 11: no runtime, no redistributable, no account. On first launch the guided tour starts; it can be replayed from Help › Guided tour. Integrated graphics start in the Eco quality preset automatically. See system requirements.

To try every feature without data of your own, File › Demo scenes generates six scenes and two pairs of clouds on the spot. See sample datasets.

Licence

The free tier views, imports, runs every process in the viewer and converts a file back out, for as long as you like. A paid edition (Desktop, Engine & SDK or Academic, each an offline key) unlocks writing out what the program worked out: drawings, rasters, reports, computed columns, meshes and videos.

To enter a key, open Help › Enter License…, paste the key (it starts N3D-) and press Activate. The tier pill at the far right of the toolbar turns from Free to Pro. The key is stored in %APPDATA%\n3d\license.key and checked on your machine; nothing is sent anywhere. The command line reads the same key from N3D_LICENSE or the --license argument.

The License window of Neurones 3D, where a licence key starting N3D- is pasted and activated offline
Help > Enter License…: paste the key, press Activate. Nothing is sent anywhere.

The interface

The Neurones 3D window: the Scene pane with Inspector, Knowledge and Results on the left, a 43 million point indoor scan in the centre, and the Properties pane with Display, AI Analysis, Compare and Navigation on the right
The whole interface: data and what it knows on the left, the view in the middle, display and analysis on the right.

Left pane: the Scene

  • Layers: every dataset in the scene, each with an eye, an identity colour, a reposition glyph and a remove glyph.
  • Inspector: the selected layer's elements, footprint, height, elevation, density and origin.
  • Knowledge: every column, tagged file or N3D, with clickable distributions.
  • Results: what has been built, each with open to bring it back.

Toolbar, left: the menus

  • File: open, add a layer, projects, demo scenes, video to 3D, images, flythroughs, exports and reports.
  • Process: every process, in the usual order, from decomposition to registration.
  • Help: documentation, support, feedback, the guided tour, the licence and About.

Toolbar, right of the menus: how you look

  • View toggles: frame the scene, ground grid, eye-dome lighting, surface reconstruction, fly navigation, 2-D sections.
  • Point views: Primitives, Classes, Segments and Instances, one at a time; each appears once its data exists.
  • Tier pill at the far right, Free or Pro; click it for the licence. Beside it, the Properties panel toggle.

Right pane: Properties

  • Display: point size, colour by, surfels, quality presets, the voxel view.
  • AI Analysis: segmentation and the N3D Classifier with its four models.
  • Compare & detect change: deviation, M3C2, conformance bands, regions.
  • Navigation: fly mode, the camera, and the flythrough recorder.
The Neurones 3D top bar: the File, Process and Help menus, then the view toggles and the four point views, and the Free or Pro tier pill at the far right
Menus on the left, view toggles and point views after them, the tier pill on the far right.
The Scene pane of Neurones 3D: a layer with its identity colour, the Inspector with footprint and height, the Knowledge list tagging each column as from the file or computed by N3D, and the Results list
The Scene pane: the layer, then what is known about it, then what has been built from it.
The Properties pane of Neurones 3D with the Display card open: point size, colour by RGB, Height or a scalar field, surfels, eye-dome lighting, the Eco, Balanced and Premium quality presets and the voxel view
The Properties pane: Display on top, then AI Analysis, Compare and Navigation.

The status bar at the bottom shows progress with a Cancel button for any running job, and the version and build date on the right.

The usual order

Most jobs follow the same path. Each step builds on the one before, and each links to its guide.

  1. Load
  2. Inspect
  3. Segment / classify
  4. Decompose / label
  5. Build: scene graph, floor plan, terrain, mesh
  6. Measure
  7. Report / export
Step nine of the Neurones 3D guided tour, The usual order: Load, Inspect, Segment or classify, Decompose or label, Build, Measure, Report or export
The guided tour’s ninth step: the usual order of work.

Escape, one level at a time

Esc undoes exactly one level of whatever you are in, the innermost first, so a stray key never throws away more than the last thing. In order: a box or lasso being dragged, the panorama, fly mode, a floor-plan note waiting to be placed, the measurement in progress, the measure tool itself, a selection in the labelling grid, a soloed class, the locked 2-D section view, the section tool, and last the most recently opened tool window, which is minimised to the tray rather than closed.

So while measuring, the first Esc clears the measurement and the second leaves the tool. Esc never acts while you are typing in a field or have a menu open.

Every guide

Load and view

Load and view Open files, add layers and convert formats Open a scan, a model or a splat capture, bring a second dataset into the same scene as a layer, and turn splats or a mesh into a real point cloud the rest of the pipeline can work on. Load and view Navigate, fly and record a flythrough video Move around the scene with the mouse or like a game, record the camera as you go, and bake the path into one MP4 per render mode. Load and view Display, quality presets and the voxel view Change how the data looks without changing the data - colour by any column, points or surface, a quality preset that suits the GPU, and a voxel view up to 2048 cells a side. Load and view Inspector, Knowledge and export columns The left pane says what a dataset is (its footprint, height and density), what it knows (every column, from the file or computed by N3D) and what has been built from it, and the export dialog writes exactly that.

Measure and cut

Measure and cut Measure distance, area and volume Pick points for coordinates and distances, trace a polygon for an area, and measure a volume in three clicks’ worth of stages - trace the base, set the height of the prism, commit - and read both the extrusion and the material the points actually fill below its ceiling. Measure and cut 2-D sections and orthoimages Cut a slab through the cloud at any height, or a vertical section at any angle, see it live in 3-D, lock into an orthographic view to read it like a drawing, and save it as an image at full point density.

Understand the scene

Understand the scene Unsupervised segmentation Break the scene into coherent surface patches (walls, floors, table tops, pipe runs) with no training data and no parameters to tune, and get a segment column for every point. Understand the scene Classify a point cloud (four models) Label every point with one of four trained models (Indoor, Outdoor aerial LiDAR, Powerlines, Streetscape), read how sure the model was from a per-point confidence column, and split a powerline corridor into individual trees, spans and poles. Understand the scene Decompose into primitives Turn a scene of millions of points into a few hundred pieces a person can actually review (planes by size, cylinders, linear runs and clusters), each point carrying its component and its primitive_kind. Understand the scene Label components A supervised review grid over the components in hand (primitives, segments or classes), with a brush per class, box and lasso in the view, a bulk selector by height, size and footprint, and a baseline so the model and the human can be compared. Understand the scene Ground filter Drop a simulated cloth on the upside-down cloud to fit the ground, label every point ground or off-ground, and measure each point’s height above that ground, with no training data and parameters you can adjust live. Understand the scene Transfer a column from a layer Work on a light subsample, then project the answer (a classification, a segment id, a height) onto the full-resolution cloud, and leave a point with no source in range empty rather than guessing.

Compare and register

Compare and register Compare and detect change (M3C2) Compare a survey against a reference (another survey, a mesh or a BIM model) as a signed distance with conformance bands and a worst-first list of defects, or run M3C2 to say what was gained, what was lost, and what simply was not observed. Compare and register Align and merge Bring a second cloud into the frame of the first automatically, see how much of it actually matched before you accept the move, place a layer by hand when you need to, and merge two splat captures into one scene.

Build deliverables

Build deliverables Terrain products (DTM, DSM, CHM, contours) Turn one ground fit into the raster set a client actually receives (DTM, DSM, canopy height, slope, aspect, hillshade, contours, trees and sunlight), all on one grid so they cannot disagree, with a README that says what is wrong with them. Build deliverables Meshing (Poisson, clean mesh, segment meshes) Three ways to a surface - screened Poisson for a smooth watertight shape, the clean mesher for a closed solid or an open façade with a texture baked from the cloud, and segment meshes for clean planar panels - each with an audit that says what the mesh is. Build deliverables Scene graph and spaces See the structure of a scene - every object as a node, spatial relations as typed edges, and the rooms they sit in, found as volumes of air rather than boxes - with areas, volumes, heights and doors per room. Build deliverables Floor plans, sections and elevations One command from raw points to a drawing set - walls between their measured faces, doors with their swing, windows with their glass, dimension chains, room areas and levels, a legend, a scale bar and a north arrow - plus sections and elevations placed where they show the most. Build deliverables Vector layers and GIS Put the design drawing beside the survey of what was built - GeoJSON, Shapefile, DXF, SVG or CityGML over the scan, in the same frame - with a coordinate-system check, and write the building back out as GIS data.

Models, splats and video

Models, splats and video USD, IFC and STEP models Open a USD stage fully composed (references, payloads, variants, prototypes and instancing resolved), an IFC building or a STEP part, switch components on and off, fly to any of them, and measure a scan against the model’s surface. Models, splats and video Gaussian splats and level of detail Stand inside a photoreal Gaussian splat capture (PLY or SPZ), draw it through a level-of-detail tree that keeps large captures fast, turn it into a real point cloud, or mesh it into a three-level glTF chain for a game engine. Models, splats and video Video to 3D (experimental) Walk through a place with a camera and get the place back as a coloured point cloud, on your own machine, with a choice of reconstruction engine. Experimental - how well it works depends on the capture.

Deliver

Deliver Reports One self-contained HTML document from what the session measured - the as-built review with its per-zone punch list, the volume and how much of it rests on the classification, the measurements you kept - and a provenance block that lets someone else re-derive every number. Deliver Export a point cloud (LAS, PLY, CSV, USD, web) One dialog for every point cloud export - format, subsample, colours, label columns and scalar fields - with a LAS writer that puts the class in the classification byte and every id in an exact 32-bit extra byte.

Stuck?

Search above, read the FAQ, or ask a person. From the app, Help › Send Feedback… copies your message with the version and build attached, ready to paste.

About

Why Neurones 3D exists.

Standing inside a 43.5 million point indoor laser scan rendered by Neurones 3D

I have spent years working with point clouds, and for most of them the software got in the way. I wanted one tool I would actually reach for every day: fast enough to enjoy, honest about what it does, and calm to use.

Neurones 3D started in Python, the way most of my research does. It worked, but it was heavy, and heavy tools quietly discourage you from opening them. So I rebuilt everything in Rust, from the file readers to the renderer, with one rule: stay frugal. A single small file, no cloud, no telemetry, billions of points on a laptop that is ten years old. In an age where every tool reaches for a data center, I wanted the opposite.

The goal is simple to say and hard to earn. One package that carries you from capture to understanding to deliverable, without exporting to five other programs along the way. Load a scan, a splat, a building, a phone video. See it, classify it, measure it, and send out something real. Together, in one place.

This is the tool I always wanted. I hope it becomes yours too.

Dr. Florent Poux 3D Geodata Academy

Get Neurones 3D

Free tier, no account, one 15 MB file. We send the download link to your inbox.

Check your inbox

We sent a confirmation to your address. Click the link inside and the download follows right after. The link stays valid for 72 hours.

If Windows shows "Windows protected your PC", that is SmartScreen meeting a build that is not code-signed yet, not a virus: choose More info, then Run anyway. Check the file's fingerprint first if you like.

Double opt-in, no spam. Your address never leaves 3D Geodata Academy. Privacy.

Cookie settings

Choose what this site may store in your browser. Strictly necessary items are always on, because the feature you asked for does not work without them. Everything else is off until you switch it on. Your choice is kept in this browser for six months.

Strictly necessaryAlways on

Needed for a feature you use. Never used to track you.

NameKindWhat it is forKept
n3d_boardCookie, HttpOnlyA random voter token set by the board (roadmap), so one browser counts as one vote.12 months
n3d-feedback-draftLocal storageA draft of the feedback form, so a refresh does not lose your message. It never leaves your browser and is cleared when you send.Until sent
n3d_consentLocal storageThis choice.6 months
Analytics

None in use today. If a measurement tool is ever added, it stays off until you allow it here.

Media

None. Nothing on this site embeds a player or media from another company.