Uncategorised – interloper.

3DGS of Video Game Clip

root — Thu, 02 Apr 2026 16:51:38 +0000

Here we have the result of a pretty boiler plate example of open-source gaussian splat scene generation. This was rendered via RealityScan for the sparse point cloud mapping and image extraction, then onto LichtFeld Studio for splat generation. I use a combination of a thread ripper cpu and an RTX 5070ti so this only took around 3 minutes to compute.

I wanted this experiment to utilise datasets that are not of pristine origin. So many spats source from existing point cloud datasets and newer high resolution cameras rigs or drones. The software required to generate these have become much more flexible in what can be ingested and I was curious if incomplete or unreal datasets could make something interesting.

Click to see the result

3DGS

root — Thu, 07 Aug 2025 08:53:33 +0000

Attempt to create a new 3DGS Viewer

root — Mon, 04 Aug 2025 13:00:17 +0000

Custom 3DGS viewer

This is my attempt to create a 3DGS viewer of my own. It is largely a fork of the Three.js libraries with some tuning to help (attempt) to alter vertices in realtime. This cannot be done with some more popular viewers such as the wonderful one provided by SuperSplat. They encode the .ply file into a Base64 image and the rest of the code is minified so forget about it. There is room to make entirely realtime 3DGS editor but this will take some time.

Hello world!

root — Tue, 03 Oct 2023 16:05:35 +0000

Working

This is a test.
How does this look now?

Engram

root — Thu, 03 May 2018 18:30:01 +0000

Following from my research into digital entropy, I stumbled across the papers of Trinity professor Thomas Ryan and his work on the ‘engram’.

With the concept of the Engram, I generally resist the comparison of the human brain to a computer, used as analogues of one another. However, the notion of the engram supports some correlations, suggesting that ‘space’ and ‘encoding’ are analogous to bits and bytes.