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
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
A trainable adapter for 3D generators that introduces explicit geometric control via typed constraint meshes (hull, avoidance, touch).
jan-niklas-dihlmann
Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
An RL framework that fine-tunes image layer decomposition models using VLM-as-judge rewards, eliminating paired supervision.
ciara-rowles
Single Image BRDF Parameter Estimation with a Conditional Adversarial Network
Creating plausible surfaces is an essential component in achieving a high degree of realism in rendering. To relieve artists, who create these surfaces in a time-consuming, manual …
