Type a name, or just describe what you need. Results blend keyword and meaning-based search. 97 matches, each with an EU availability status.
Model
3D reconstruction model that recovers geometry and camera poses from photos or video using a loop transformer.
Model · Google DeepMind
Google DeepMind world model that turns text or images into interactive, real-time controllable worlds with audio.
Research
Research framework that turns a single image into a textured 3D asset with articulated parts and physical behavior.
Research · Meta
Meta/Oxford multi-agent video world model that adds fixed auxiliary cameras to keep a shared world consistent.
World model that turns a few context images into an editable, physics-simulated 3D world rendered by a video model.
Unified motion-language model for text-to-motion, motion captioning, completion and editing, from HKUST and Tencent Games.
Model · Skyfall
Engineering world model from Skyfall that decomposes mechanical objects into CAD parts and generates floor plans.
Post-training method that refines feed-forward 3D reconstruction models (Pi3, DA3, VGGT) on unlabeled video.
Research method that rigs animatable Gaussian characters with an inner kinematic skeleton and outer free-form bones.
Model · Odyssey
Odyssey 3 is an interactive world model from Odyssey that generates explorable, steerable simulated environments.
Model · NVIDIA
NVIDIA research system where a code game engine drives a two-step streaming MiniMax-H3 video model for real-time rendering.
Model · ByteDance
Unreleased, unnamed ByteDance world model demoed in Beijing for novel camera paths and text-to-world generation.
Viggle's physics-native world foundation model that generates 3D scenes, rig-free characters and motion from text or images.
Research · Microsoft
Experimental Microsoft Xbox research effort exploring AI for game preservation, reverse-engineering and AI-generated games.
Real-time interactive world model with compressed memory and hybrid action and semantic control, built on Wan 2.2.
Agentic framework that reconstructs sim-ready 3D scenes with rigid, articulated and deformable objects from multi-view RGB.
Monocular video motion capture that combines flow matching with physics-based RL for plausible 3D human motion.
Research framework for long, consistent video generation using a persistent 3D world state as memory.
Feed-forward 3D Gaussian Splatting model that reconstructs scenes from arbitrary input views, with or without camera poses.
Model · Nvidia
Feed-forward model that repairs lifted 2D tracks and depth into accurate dense 3D trajectories from monocular video.
Research model that builds complete 3D assets from sparse, unposed images by jointly doing reconstruction and generation.
Model · Meta
Meta research framework that aligns a frozen SAM 3D model to input images or video at inference time for 3D reconstruction.
NVIDIA research model that turns a single image into a queryable 3D Gaussian scene with semantics and object instances.
Research multi-player video world model with hierarchical communication, trained on 4 players and run with up to 10.
