7 posts tagged with "gaussian-splats"

Today, we are releasing PlayCanvas Engine 2.7.5 that introduces a new and advanced compression format for 3D Gaussian Splatting (3DGS) called Self-Organizing Gaussians (SOGS). SOGS can reduce 3DGS data by over 20x.

To showcase PlayCanvas' support for SOGS, we have collaborated with Christoph Schindelar to build a technical demo:

RUN FULLSCREEN IN A NEW TAB

The church scene above was originally a 1GB PLY file containing 4 million Gaussians - not at all suitable for the web or mobile! Using SOGS, we can serve up the scene in just 55MB! Read on to find out how.

Today, we are announcing the open sourcing of the SuperSplat Viewer. Try it out for yourself:

Today, we are announcing the release of SuperSplat 2.2. 🚀

SuperSplat is your open source platform for editing and publishing 3D Gaussian Splats. This update introduces video rendering for your splats, alongside numerous other improvements. Let's dive in!

Today, we are announcing a major update of SuperSplat, the open source platform for editing and publishing 3D Gaussian Splats.

CLICK HERE to open in a new tab. Credits: Splats scanned at the V&A Museum. HDRI from Poly Haven.

We have big news for the 3D Gaussian Splat community - the PlayCanvas Editor now has fully integrated support for splats! Learn how to quickly build stunning, interactive 3DGS applications today.

Today, we are announcing the latest release of SuperSplat, the open source tool for editing and optimizing 3D Gaussian Splats. If you don't have a PLY file to hand, here's an example!

Introduction​

3D Gaussian Splatting is a new method for digitizing and rendering real world objects. With gaussian splatting, you can digitize a scene from a few photos using services like Luma Labs or Polycam. These services take the set of photos and generate a 3d Gaussian Splat scene in PLY format.

For example, this is a Gaussian Splat scene rendered in PlayCanvas.