The scenes coming out of The Latent Space (a collaboration with Alejandro Cartagena / @halecar2 ) are now becoming explorable world fragments. Using the LoRAs trained on Alejandro's datasets, paper compositions on my desk are passed through the realtime Diffusion pipeline, then turned into 3D Gaussian Splats using ML Sharp.
#diffsuion#GaussianSplatting#MLSharp#SparkJS#AI
A sample of the world fragments from yesterday's Hands-on Hallucination session.
Physical interfaces → real-time img2img diffusion → 3D GS → real-time rendering in a browser on desktop, mobile and AVP.
#diffsuion#GaussianSplatting#MLSharp#SparkJS#AI
Accelerated capture from yesterday's Hands-on Hallucination session. I started out testing the system alone, then my son joined in and quickly took control; deciding which generated frames to freeze and transform into 3D Gaussian Splats. We ended up with a series of strange little world fragments.
Physical interfaces → real-time img2img diffusion → 3D GS → real-time rendering in a browser on desktop, mobile and AVP.
#GaussianSplatting#AppleML#MLSharp#SparkJS
I resumed work on my Hands-on Hallucination ML Sharp experiments from ~5 months ago. I manipulate paper, clay, etc. in front of a camera, watch a real-time diffusion pipeline hallucinate a world from them, press a knob, and the frozen frame becomes a 3D Gaussian Splat, instantly explorable in the browser or in VR.
#GaussianSplatting#AppleML#MLSharp#SparkJS
I am releasing the “MLSharp” app for macOS.
MLSharp is a premium macOS application that transforms 2D images into immersive 3D Gaussian Splatting (3DGS) models using state-of-the-art AI.
suto.bex.jp/mac/mlsharp/inde…
I’m using Blender natively to import Apple ML-Sharp Gaussian Splatting. ✨
Controlling focal point, camera parameters and parallax directly inside Blender opens the door to entirely new workflows.
The result is seriously impressive. 🔥
#b3d#MLSharp#GaussianSplatting
built a synthetic drone perception pipeline:
- photorealistic scene generation and temporal dynamics to create (real synth data) for robust models
- real-time detection tracking trajectory prediction models
- temporal 3D reconstruction using #mlsharp
visualised in @playcanvas supersplat
Couldn’t resist testing ML-Sharp by @Apple. Both Pano2Room and ML-Sharp share the same issue: unseen angles in the input lead to sparse point clouds. Using Sony’s open-source as a preprocessing step gives some interesting improvements.
#mlsharp#supersplat