Auteur: Language-Driven Cinematographic Framing for
Human-Centric Video Generation

Abstract

Generative video models have achieved remarkable visual fidelity and temporal coherence, yet intentional camera control remains elusive. Existing frameworks treat camera motion as a byproduct of pixel synthesis, producing trajectories that are stochastic, spatially inconsistent, and indifferent to the human subject driving the scene. In this work, we present Auteur, a method for language-driven, human-centric camera framing in generative video. Our core insight is that professional filmmakers conceive shots not as world-space trajectories but as framings defined relative to the actor, encoding shot size, angle, and composition as functions of human pose and motion. We formalize this intuition as a human-centric camera parameterization and introduce a Domain-Specific Language (DSL) that is convertible to standard 6-DoF camera parameters. A fine-tuned multimodal large language model then acts as a virtual director, mapping natural language descriptions and coarse human motion to sparse DSL keyframes that are deterministically interpolated into continuous camera trajectories, which are then provided as input to video generators. We train and evaluate Auteur on a new dataset of 34K aligned text, human motion, and DSL-annotated camera trajectories drawn from procedural synthesis and real-world movie footage from the CondensedMovies dataset. Auteur enables cinematographic framing of human-centered scenes, a capability largely absent in prior generative models. To assess this behavior, we propose new framing-focused metrics, and our experiments show that Auteur consistently outperforms existing methods on actor-centric framing and subject visibility.

Cross-Renderer Generalization

Auteur outputs a standard 6-DoF trajectory, so it drives independently built generators without modification. Below, the same predicted trajectory is rendered through three different camera-conditioned generators and compared against a text-only baseline that receives the same prompt but no explicit trajectory. Every Auteur-guided renderer follows the requested framing more faithfully than the baseline.

BibTeX

@article{kizil2026auteur,
  title   = {Auteur: Language-Driven Cinematographic Framing for
             Human-Centric Video Generation},
  author  = {Kizil, M. Burak and Sanli, Enes and Mitra, Niloy J. and
             Chen, Xuelin and Erdem, Erkut and Erdem, Aykut and
             Ceylan, Duygu},
  journal = {arXiv preprint},
  year    = {2026}
}