Magical Particle Generator Made with Apple's SHARP Model
Tyler J Cagle turned an image into Gaussian splats.
Developer Tyler J Cagle presented his particle generator that accepts an image and turns it into a Gaussian splat using Apple's SHARP model, an "approach to photorealistic view synthesis from a single image," which regresses the parameters of a 3D Gaussian representation of the scene.
"The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements."
3D Gaussian Splatting is a rendering technique that leverages 3D Gaussians to represent the scene, thus allowing one to synthesize 3D scenes out of 2D footage. Simply put, it takes samples of images and turns them into 3D scenes without creating meshes by converting a point cloud to Gaussians using machine learning. You can learn more about it here.
Cagle's showcase demonstrates structures that look like dream sequences, all fuzzy and ethereal, taken from photos. The app can change the number and size of particles and adjust other parameters.
The project was inspired by Cullen Webber's particle flow field, created with Three.js in WebGL.
It seems like the files produced by the generator are pretty large, but this is still a great experiment that would be cool to use in production.
Gaussian splatting is not novel anymore, with developers making plug-ins for Unreal Engine 5 and Cinema 4D, explosions, and even bees.
Follow Cagle on X/Twitter for more and don't forget to subscribe to our Newsletter and join our 80 Level Talent platform, follow us on Twitter, LinkedIn, Telegram, 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.
