Mac · Windows · Linux · on-device

3D Gaussian splatting
for everyone.

Three easy steps, one window, nothing in between: 1choose a folder of photos, a video or a lidar scan, 2press Run All, 3watch the scene take shape as it trains. LuluSplat extracts the frames, solves the cameras and trains a photorealistic 3D Gaussian Splat you can orbit, with no separate tools to install, entirely on your own GPU, on Mac, Windows or Linux. No uploads, no account, no subscription.

The direct downloads are completely free. Get it from the Mac App Store or the Microsoft Store to support development and receive automatic updates.

  • Mac · M1 or later · Metal · 179 MB
  • Windows · 10/11 · Vulkan · 247 MB
  • Linux (beta) · Vulkan · 262–265 MB

LuluScan: an even easier way to scan anything Coming soon

The scanner is the phone you already have. LuluScan is a companion app on the way for iPhone, iPad and Android: as you shoot, it records where the phone was for every photo, with LiDAR depth on devices that have it. The capture opens in LuluSplat with Import COLMAP Data and trains from the phone's own camera positions, with no camera solve.

Fig. 01 — LuluScan · room guideFrom the app

Walk round the room with your back to the walls, pointing the phone across the room at the far side — not at the wall beside you. Go round once holding the phone level, then again tilting down at the floor and up at the ceiling. Step sideways between shots; don't turn on the spot.

Reading the map

While you capture, this map sits in the top corner of the camera. It shows what has been photographed so far; the percentage is how much of the capture is done.

  • A compass of where the camera has looked. Up is roughly the way you faced when the camera opened.
  • The middle band lights for shots held level, the outer band for shots tilted down at the floor, the inner band for shots tilted up at the ceiling.
  • The needle is the way the camera faces now.
  • Fill the middle band all the way round, then the floor. The ceiling counts least. The number of photos counts too.
  • Cameras from the phone Each photo keeps the position the phone's tracking gave it, so training starts without a camera solve.
  • LiDAR depth and normals On devices with LiDAR, depth and normal maps come with the capture and guide training.
  • Without LiDAR, too Where the phone's tracking is thin, LuluSplat fills in the point cloud from the photos and keeps the phone's cameras where they are.
  • Settings and up, included A focus region for an object, more iterations for a room, and the phone's gravity for which way is up.

LuluScan is in development. The animation is its guide for a room, as the app plays it before a capture: the walk on the left, the coverage map filling on the right. A video capture from LuluScan opens with New from Media and is solved like any other.

Fig. 02 — media in, splat and mesh out
A full run in LuluSplat 1.3.2 on a Mac mini M4 with 24 GB: 185 photos to a trained splat to a textured mesh.
  1. 01

    Ingest

    Stills, video, 360° photos and video, Insta360 .insv, or a lidar scan — mixed in one scene.

  2. 02

    Extract

    Frames pulled from clips, blurry ones rejected at a threshold you set.

  3. 03

    Solve

    COLMAP, Depmap or Speedmap places the cameras and builds a point cloud, checked before training starts. A lidar scan brings both with it.

  4. 04

    Train

    Vanilla or MCMC on your own GPU — Metal on Mac, Vulkan on Windows and Linux.

  5. 05

    Export

    .ply and .splat, an optional textured .glb mesh and .obj collider, and a run log.

01 How it works

Three steps from footage to a scene you can orbit.

Step 01 / 03

Drop in your media

A folder of stills, ordinary video, 360° video and photos, Insta360 dual-fisheye clips, or an E57 lidar scan with its 360° photos — several at once, mixed together, in a single scene. Camera positions are solved for you, or taken straight from the scan.

Shot on a phone, an action cam, a DSLR or a lidar scanner — it all works.

The LuluSplat start screen offering new capture from media, reopening a project, importing COLMAP data, or batch processing.

Step 02 / 03

Problems caught early

Blurry frames are dropped as they are extracted, and the reconstruction is checked before the long training step. A capture with too little overlap is flagged in seconds rather than an hour in.

A blur threshold you can tune, and a warning that says plainly what went wrong.

LuluSplat showing blur-rejection settings and a red warning that the sparse reconstruction is too thin to train, advising a re-capture with more overlap.

Step 03 / 03

Watch it converge

Orbit the scene as it trains — rough at first, sharpening as it goes. Switch the live viewport off for a faster run.

Full console output, and a RAM readout for the run in progress.

A finished LuluSplat scene of a garden table rendered photorealistically in the viewport at 690,588 splats.

02 Features

Built for the whole capture, not just the pretty part.

01

Photos, video, 360° and lidar

Stills, ordinary video, 360° video and photos, Insta360 dual-fisheye clips, or an E57 lidar scan with its 360° photos — several at once, mixed, in a single scene. Both lenses are solved, and the camera operator is masked out automatically.

02

Problems caught early

Blurry frames are dropped as they are extracted, and the reconstruction is checked before the long training step — so a thin capture is flagged in seconds, not an hour in.

03

Two ways to train

Vanilla grows splats wherever detail is missing. MCMC trains a fixed number and keeps moving them to where they help most, with memory known before it starts. Train a project with each and compare.

04

Native on Mac, Windows and Linux

Reconstruction and rendering run on your own GPU — Metal on Apple silicon, Vulkan on Windows and Linux. No cloud instance, no queue, nothing to rent.

05

Three ways to solve the cameras

COLMAP, the proven choice; Depmap, which reads depth from every photo and copes with captures that barely move; or Speedmap, a fast on-site check of your frames. Already have COLMAP data? Import it and skip straight to training. A lidar scan skips the solve too: the scanner already knows where every photo was taken.

06

Completely private

Your photos, video and scans never leave the machine. Nothing is uploaded, there is no queue to wait in, and it all works offline.

Lidar scans: no camera solve

Open an E57 lidar scan with its 360° photos, such as an FJD Trion export, and LuluSplat trains from it directly. Each photo is placed where the scanner took it, so there are no cameras to solve. Training starts from the scan's own points, and its measured depth guides it. An FJD Trion P2 capture folder opens as it comes off the scanner, with no export step, and 360° or fisheye footage of the same walk is placed among the scanner's photos.

Fig. 03 — Lidar points
A parking garage as a lidar point cloud: dense rows of points trace the columns, the cars, the ceiling beams and the floor.

The scan · measured, not estimated

The points come from the scanner itself. Training starts from them instead of from a solved point cloud, so the columns, ceiling and floor are in place from the first step.

Fig. 04 — Splat
The trained 3D Gaussian Splat of the same garage from the same viewpoint: white concrete columns, parked cars, painted bay lines and the stained ceiling, photorealistic.

The splat · the result

The trained scene from the same viewpoint. Every photo sat where the scanner took it, and the scan's depth kept the walls, ceiling and floor where they were measured.

COLMAP and Depmap, side by side

A carved chamber at Medinet Habu, solved both ways. This capture is a hard case: there's no lidar scan, so the cameras have to be solved from the photos alone, and every photo was taken from the middle of the room, turning on the spot to face the walls.

Fig. 05 — COLMAP
The Medinet Habu chamber solved with COLMAP: a sparse, broken-up cloud of 117,702 points, with all the cameras bunched at the centre of the room inside a red circle.

117,702 points · 139 cameras

The red circle marks where the cameras are: all at the centre of the room. With almost no movement between shots, feature matching has little to triangulate from, and the walls come out sparse and broken up.

Fig. 06 — Depmap
The same chamber solved with Depmap: a solid, box-shaped cloud of 625,061 points with the carved reliefs visible on the walls.

625,061 points · 145 cameras

Depth is measured in each photo on its own, so it doesn't need the camera to move. Depmap places 145 cameras to COLMAP's 139, and the chamber comes out as solid walls, with over five times the points.

Fig. 07 — the final splat
The trained scene from this capture, with the reliefs on every wall and the ceiling. Explore it in 3D on SuperSplat
Trained with
Vanilla · 15,000 iterations · 5M splat budget · SH degree 3
Options
Depth guidance · normal guidance · finer growth · anti-aliasing
Result
scene.ply · 1.24 GB
Machine
Mac mini M4, 24 GB · LuluSplat 1.2.2

Depth and normals, read from every photo

For each photo, LuluSplat estimates how far away every pixel is and which way every surface faces, using the MoGe-2 model on your own GPU. MoGe-2 is built into LuluSplat, so there's no model to download and nothing extra to set up. Training can then lean on that geometry instead of guessing it from colour alone.

Fig. 08 — Depth
Depth map of a small house photographed from above: nearer surfaces are lighter, the background fades to dark grey.

Depth · nearer is lighter

How far each pixel is from the camera. Depmap uses it to place the cameras and seed a dense point cloud, and depth guidance pulls the scene's shape toward it.

Fig. 09 — Normals
Normal map of the same house: each surface is coloured by the direction it faces, so the roof planes, walls and ground read as distinct colours.

Normals · colour is direction

Which way each surface faces. Normal guidance turns every splat to lie flat along those surfaces instead of floating at odd angles.

Fig. 10 — Splat
The trained 3D Gaussian Splat of the house: tiled roof, corrugated awning, rough plaster walls and the surrounding grass, photorealistic.

The splat · the result

The trained scene: photorealistic, and ready to orbit, export as a splat, or turn into a mesh.

  • Fewer floaters Depth keeps splats on real surfaces, so there's less haze hanging in empty air.
  • Flatter walls, cleaner edges Walls, floors and roofs come out as surfaces, not lumpy clouds.
  • A head start Depmap begins training from a far denser point cloud, so the subject is covered from the first step.
  • Better meshes Splats that face the right way make a cleaner textured mesh and collider when you export one.

Depth guidance and normal guidance are quality options, off by default — switch them on per project.

Auto masking: the operator left out

In 360° and fisheye footage, whatever carries the camera is in every frame and moves with it: the person holding it, the stick, the helmet or the drone. LuluSplat finds it on its own, for each lens and each view of a 360° frame, from what stays put in the picture from frame to frame and where a person keeps appearing. It's left out of the camera solve and of training. People who appear only now and then, the ones being filmed, are kept.

Fig. 11 — Frames view · masks tinted
LuluSplat's Frames view for an Insta360 .insv walk through a kitchen, 148 frames: in each fisheye frame the area outside the lens and the operator holding the camera are tinted red, the parts left out of solving and training. In a few frames only the stick is tinted. On the left, the Obstructions settings are outlined in red: Find automatically, switched on, and the Hide below, Crop bottom, Trim edges and Crop edges sliders.
An Insta360 .insv walk through a kitchen, 148 frames. Tinted is what's left out: the edge of the lens, and the operator under the camera. In a few frames only the stick is caught. Outlined on the left: the Obstructions settings, with Find automatically on and the sliders for what it misses.
  • On by default Find automatically sits under Prepare frames ▸ Obstructions, and runs while the frames are made. Lidar scan projects mask the scanner and its operator the same way.
  • A steadier solve Features on the operator travel with the camera and pull the solve about. Masked, they're never matched.
  • Missed frames clean themselves up Where a frame slips through, the operator is in that photo alone. Every other photo of the spot shows the scene behind them, so training treats them as noise: their splats fade and are pruned.
  • See it at a glance The Frames view tints what's left out, so a mask that missed something shows at once. Masks turns the tint off.

For what the masks miss on fisheye footage, the sliders under Obstructions — Hide below, Crop bottom, Trim edges, Crop edges — leave out the bottom or the rim of every frame, from the solve or from the splat.

Speedmap: quickly verify your frames on site

A third solver, made for fast checks in the field. Right after shooting, Speedmap finds features on smaller images, uses about 300 of a long video's frames, and places every camera at once, then lists any frames it couldn't place. You know whether the capture is complete while you're still on location, and can reshoot the gaps before you leave.

Fig. 12 — left: Speedmap · right: COLMAP, global mapper

Speedmap

8 min 44 s

photos to trained splat · camera solve about 1 min

COLMAP · global mapper

15 min 33 s

photos to trained splat · camera solve about 7 min

The Speedmap run is on a Mac mini M4 with 24 GB. The same 185 photos and the same training on both: Vanilla, 7,000 iterations, a 1M splat budget. Speedmap's cameras are rougher, so its scene comes out softer — use it on site to confirm coverage, then solve with COLMAP or Depmap for the final scene.

03 Automation

Run it at volume, or without sitting in front of it.

Everything above is the whole app. These are for the days when one capture at a time is not the job.

A / Batch

Queue the captures and walk away

Line up as many captures as you like and leave the machine to it. Each becomes its own project with its own settings.

  • The list saves itself — a run interrupted overnight picks up where it stopped, finished projects skipped and failed ones retried.
  • Folders that already hold a COLMAP reconstruction go straight to training.
  • Ordinary video, 360°, and Insta360 clips can all go in together.
The LuluSplat batch panel listing four completed captures — garden_sparse, Tako01, Sala360_01 and Insta360_group — each showing its splat count, beside per-project training settings.

B / Command line

The app is its own CLI

Give it a subcommand and it runs headlessly instead of opening a window.

  • Build a capture, import a reconstruction, train again, or run a saved batch — from a script, a cron job, or a watch folder.
  • Progress on stderr, results on stdout: --json pipes straight into build systems and render farms.
  • Authorise a folder once and it works everywhere beneath it.
  • run
  • import
  • train
  • batch
  • grant
  • mcp
LuluSplat's Command Line panel, listing the run, import, train, batch, grant and mcp subcommands with their options and worked examples.

C / AI assistants

A built-in MCP server

Claude and other assistants can drive the pipeline themselves, over the Model Context Protocol.

  • Build a splat, follow it as it trains, and report on projects already finished.
  • Ask it how to shoot a capture that reconstructs well, before you shoot it.
  • Training logs are exposed as resources, so an assistant asked why a run was slow can read the timings rather than guess.
LuluSplat's AI Assistants panel, showing the MCP server configuration snippet for Claude Desktop and the list of tools it exposes.

04 Export

Finish here. Keep working anywhere.

Save finished scenes as .ply and .splat — the formats Gaussian Splat viewers, web players, and DCC plugins already read. Turn on mesh export and training also saves a textured scene.glb for game engines and 3D apps, and a low-poly collider.obj for physics, both in the scene's own coordinates. Every run also appends its splat count, quality, duration, and peak memory to output-log.txt.

  • .ply
  • .splat
  • .glb
  • .obj
  • Splat viewers
  • Web players
  • DCC plugins

Need a different 3DGS format? Use our online converter, Pebee

Need transition effects? Use our online 3DGS Transition Lab

06 Privacy

Nothing leaves your machine.

LuluSplat is developed independently at Liquidus Labs by Wilfredo Bigol Jr., an electronics and software engineer in the Philippines.

01

Nothing collected

The app has no tracking, no analytics and no account. Your photos, video, scans and trained scenes stay on your machine, and everything works offline.

02

Support development

The free downloads are the full app. Buying it on the Mac App Store or the Microsoft Store is what keeps it improving — and brings automatic updates.

03

Bugs, ideas, or specific requirements

Found a bug, want a feature, or need LuluSplat to fit a specific workflow? Send it through the contact page — every message is read.

This website is separate from the app: it uses Google Analytics to count visits and downloads. Details are in the privacy policy.

07 Get it

LuluSplat: 3D Gaussian Splat

Capture any real-world object or space, and inspect it from angles you never stood in. On your own machine, on your terms.

Mac · .dmg · 179 MB
Windows · .exe · 247 MB
Linux (beta) · .deb · .rpm · .tar.xz · 262–265 MB

The direct downloads are completely free. Get it from the Mac App Store or the Microsoft Store to support development and receive automatic updates.

Mac
Apple silicon — M1 or later · v1.3.2 · .dmg · 179 MB
Windows
Windows 10 or 11, 64-bit · Vulkan 1.1 graphics card with 4 GB of video memory or more · v1.3.2 · .exe · 247 MB
Linux
x86-64 · Vulkan 1.1 GPU driver · .deb for Ubuntu 24.04, .rpm for RHEL 9 and 10, or .tar.xz · beta · v1.3.2 · 262–265 MB
Compute
On-device GPU — Metal on Mac, Vulkan on Windows and Linux — no cloud instance
Trainers
MacMetal Vanilla (gsplat), MCMC (metal-gauss) Windows · LinuxVulkan Vanilla (gsplat), MCMC (metal-gauss)
Input
Stills, video, 360° photos and video, Insta360 .insv and .insp, COLMAP, E57 and FJD Trion lidar scans
Output
.ply, .splat, textured .glb mesh, .obj collider, output-log.txt
Automation
CLI subcommands, MCP server
Network
Not required — fully offline capable. No other tools to download.