الباحثون

Vikram Voleti

المنشورات 2

نسخة أولية وصول مفتوح

4Director: Controlling Video World Models with Rigid 3D Geometry

Wei cao, Hao Zhang, Vikram Voleti وآخرون · 2026

Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through image-plane cues that are ambiguous in depth and rotation or through 3D tracks and blobs that lack complete geometry and lose consistency across viewpoint changes. We int …

نسخة أولية وصول مفتوح

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for the optimal performance of each of these, both in terms of fidelity and semantics. Flexible-length, coarse-to-fine tokenizers yield exactly t …

المؤلفون المشاركون