logo80lv
Articlesclick_arrow
Talentsclick_arrow
Events
Workshops
Aboutclick_arrow
profile_login
Log in
0
Save
Copy Link
Share

Free Nanite-Style Tool To Render 3D Gaussian Splats In UE5

NanoGS aims to render large 3DGS efficiently while keeping VRAM usage low.

Rendering really large Gaussian Splatting files is always challenging. To do it in real-time, you have to manage VRAM carefully, sort millions of splats efficiently, and only draw the ones that actually appear on the screen. Tim Chen has released NanoGS, a free plug-in that handles optimization, making it possible to render large 3DGS files directly within Unreal Engine more efficiently.

NanoGS uses Nanite-style LOD clusters, screen-space error LOD selection, splat compaction, global accumulator, and GPU-accelerated radix sort. You can watch the video above to see how it works and download the plug-in by clicking this link.

The developer describes NanoGS as more of a proof of concept at this stage, so don't expect perfect results and feel free to report any issues on the GitHub page. Still, the community response has been very positive, with many users reporting that it works well for their projects.

For best results, Tim recommends splitting a large Gaussian Splatting file into smaller pieces, such as individual props for cinematic scenes or tiles for geospatial data. The repository includes a simple Python tile slicer to help with this.

Follow the developer on LinkedIn for more tools and projects:

Don't forget to subscribe to our Newsletter and join our 80 Level Talent platform, follow us on TwitterLinkedInTelegram, and Instagram, where we share breakdowns, the latest news, awesome artworks, and more.

Are you a fan of what we do here at 80 Level? Then make sure to set us as a Preferred Source on Google to see more of our content in your feed.

Ready to grow your game’s revenue?
Talk to us

Comments

0

arrow
Type your comment here
Leave Comment
Ready to grow your game’s revenue?
Talk to us

We need your consent

We use cookies on this website to make your browsing experience better. By using the site you agree to our use of cookies.Learn more