4Director: Controlling Video World Models with Rigid 3D Geometry
A video world model that uses rigid 3D geometry to control camera and object motion from a single image.
wei-cao
•
•
1 min read
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
A flexible video tokenizer that puts semantics in early tokens for efficient, high-fidelity autoregressive video generation.
mikhail-dereviannykh