Model that reconstructs a single image into a 3D scene with separate, individually usable objects.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Mira Scene (also referred to as Mirror Scene) is a model listed by Eden (vast-eden.ai), which describes itself as working on generative models for interaction and simulation. The official page fetched contained only a loading placeholder, so most details come from a YouTube creator summary.
According to that summary, it takes a single image and reconstructs a 3D scene by detecting objects, estimating depth and generating geometry for each object. The output is a scene with separate objects, which can be used in Blender or in physics simulators.
Code and a dataset (about 6.1 GB) are reportedly released. The license, exact release date, pricing and hosting details were not confirmed from the provided material.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Reconstructs a single image into a 3D scene with separate objects by detecting objects, estimating depth and generating geometry. Usable in Blender or physics simulators; code and dataset released, about 6.1 GB.
Closest neighbours by meaning, not just by category.
Model
Real-time multiplayer world model that generates four-player Rocket League-style gameplay, playable online.
Model
Feed-forward 3D scene reconstruction model that outputs triangle primitives directly usable as meshes for simulation.
Research
Research method that generates compositional 3D scenes from a single image via object-to-scene distillation.
Model
Research model that decomposes a single image or scene mesh into object-level 3D meshes with consistent spatial layout.
Research
Research method that turns a single photo or video into a simulation-ready 3D scene for robot reinforcement learning.
Model
Research model that unifies 3D scene generation and reconstruction in a single pixel-space diffusion model.