gaussian splat

6 Articles

Combining Photogrammetry Utilities Into A Simple GUI Tool

August 24, 2026 by 7 Comments

One of the fun aspects of open source software is that you can often find so many libraries and tools that implement the functionality you need, but ease of use for e.g. artists is often not a priority. This is where [Edin Spiegel] ‘s annoyances with photogrammetry tools led him down to the path of creating the Simple Photogrammetry GUI project, which is basically what it says on the tin.

In an associated video its development and use is demonstrated, combining tools like Colmap, OpenMVS, mvs-texturing, pymeshlab, brush and PoissonRecon to implement both photogrammetry and gaussian splatting to turn those photos into a not too shabby mesh along with realistic textures.

The GUI uses the Flutter GUI kit, so Linux support is still somewhat sketchy, but should work in this new release of this GUI wrapper. The author is asking for people to test this GUI and report any issues found so that they can be addressed.

From a quick glance at the project and the comments to the video it seems quite useful for anyone who wants to get started quickly with photogrammetry. One niggle is perhaps that it relies on processing using CUDA, with a much slower fallback to CPU processing if you do not happen to have an Nvidia-blessed GPU installed. Of course this is one of those universal issues in a world where theoretically everyone should be using OpenCL already.

In addition to the build instructions you can also download an AppImage for Linux and compiled binaries for Windows to theoretically get started as fast as your internet connection allows. Interestingly, the AppImage is well over a GB in size, whereas the Windows ZIP file is just 207 MB for the v1.1.5 release, so take that into account.

Continue reading “Combining Photogrammetry Utilities Into A Simple GUI Tool” →

Watch Soldering Up Close And From Any Angle, In VR

August 18, 2026 by 28 Comments

A manual skill like soldering is so much easier to learn and grasp when one can watch it in action, and there’s a brand new way to do that using virtual reality (VR). It isn’t just a series of 3D videos shot at someone’s workbench, either.

See soldering in action from any angle, with fine details preserved even close up.

PCB Hand-Soldering Basics is a series of thirteen videos that demonstrate soldering using Gaussian splats, a method of displaying 3D content that allows the viewer to freely look at things from any angle. Gaussian splats aren’t new, but what makes this different is the sheer level of detail and the fact that it’s focused on handheld tool use rather than displaying a famous location, landmark, or something similarly “big”.

Throughout the videos fine detail on the iron, parts, and the PCB itself remain visible from any angle and even from close up. Here’s a short video captured from within a VR headset that is probably the next best thing to seeing it yourself.

An educational production, it was was made in cooperation with the Department of Electrical and Electronic Engineering at Imperial College London. A few more details are in a LinkedIn post by [Tanmay Lad], who was part of the team involved in the production. The goal is to offer a unique, front-row seat to hand soldering with the ability to zoom in or look at it in 3D from any angle.

Not familiar with Gaussian splats? We’ve previously covered a great overview. They look great and are computationally cheap to render, and being able to get up close and see such detail is not really something one expects.

Extract 3D Video Game Content By Firing Up Photo Mode

May 17, 2026 by 11 Comments

Here’s a pretty clever method [Dung3onlord] used to capture 3D scenes from a PlayStation 5 without needing any specialized software. All that’s needed is a series of high-resolution screenshots, and a few software tools.

The process is essentially photogrammetry, it just uses screenshots as the input instead of photographs.

Instead of sneakily yanking 3D assets from the runtime, he fires up the game’s photo mode on his PS5. By capturing an orbiting video of a static scene (making sure to hide the game’s user interface, something photo mode in games is good for) he ends up with a video file whose content — essentially a series of screenshots — can be used to reconstruct the original 3D scene. The workflow [Dung3onlord] uses has rather more steps, but conceptually that’s all there is to it.

The whole process is remarkably similar to photogrammetry, a method of turning a bunch of photographs from different angles into a 3D point cloud. We’ve seen photogrammetry used to digitize objects because point clouds can be turned into 3D models, essentially allowing one to 3D scan an object using little more than a digital camera.

Continue reading “Extract 3D Video Game Content By Firing Up Photo Mode” →

Learn What A Gaussian Splat Is, Then Make One

October 31, 2025 by 16 Comments

Gaussian Splats is a term you have likely come across, probably in relation to 3D scenery. But what are they, exactly? This blog post explains precisely that in no time at all, complete with great interactive examples and highlights of their strengths and relative weaknesses.

Gaussian splats excel at making colorful, organic subject matter look great.

Gaussian splats are a lot like point clouds, except the points are each differently-shaped “splats” of color, arranged in such a way that the resulting 3D scene looks fantastic — photorealistic, even — from any angle.

All of the real work is in the initial setup of the splats into the scene. Once that work is done, viewing is the easy part. Not only are the resulting file sizes of the scenes small, but rendering is computationally simple.

There are a few pros and cons to gaussian splats compared to 3D meshes, but in general they look stunning for any kind of colorful, organic scene. So how does one go about making or using them?

That’s where the second half of the post comes in handy. It turns out that making your own gaussian splats is simply a matter of combining high-quality photos with the right software. In that sense, it has a lot in common with photogrammetry.

Even early on, gaussian splats were notable for their high realism. And since this space has more than its share of lateral-thinkers, the novel concept of splats being neither pixels nor voxels has led some enterprising folks to try to apply the concept to 3D printing.

Move Over, Lithophane: 3D Printed 3D Photos With Gaussian Splats

May 10, 2025 by 24 Comments

If you had asked us yesterday “How do you 3D Print a Photo”, we would have said “well, that’s easy, do a lithophane”– but artist, hacker and man with a very relaxing voice [Wyatt Roy] has a much more impressive answer: Gaussian splats, rendered in resin.

Gaussian splats are a 3D scanning technique aimed at replicating a visual rather than geometry, like the mesh-based 3D-scanning we usually see on Hackaday. Using photogrammetry, a point cloud is generated with an associated 3D Gaussian function describing the colour at that point. Blend these together, and you can get some very impressive photorealistic 3D environments. Of course, printing a Gaussian smear of colour isn’t trivial, which is where the hacking comes in.

Continue reading “Move Over, Lithophane: 3D Printed 3D Photos With Gaussian Splats” →

Generating 3D Scenes From Just One Image

December 29, 2023 by 6 Comments

The LucidDreamer project ties a variety of functions into a pipeline that can take a source image (or generate one from a text prompt) and “lift” its content into 3D, creating highly-detailed Gaussian splats that look great and can even be navigated.

Gaussian splatting is a method used to render NeRFs (Neural Radiance Fields), which are themselves a method of generating complex scenes from sparse 2D sources, and doing it quickly. If that is all news to you, that’s probably because this stuff has sprung up with dizzying speed from when the original NeRF concept was thought up barely a handful of years ago.

What makes LucidDreamer neat is the fact that it does so much with so little. The project page has interactive scenes to explore, but there is also a demo for those who would like to try generating scenes from scratch (some familiarity with the basic tools is expected, however.)

In addition to the source code itself the research paper is available for those with a hunger for the details. Read it quick, because at the pace this stuff is expanding, it honestly might be obsolete if you wait too long.