# PACE: Precise AI Cinematic Expression

arXiv: https://arxiv.org/abs/2609.19853 · HTML: https://mlsanity.com/paper/2609.19853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 40 of its 64 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 40)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [MovieNet: A Holistic Dataset for Movie Understanding](https://mlsanity.com/paper/2007.10937/) (2020)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Narrative Planning: Balancing Plot and Character](https://mlsanity.com/paper/1401.3841/) (2014)
- [Movie Plot Analysis via Turning Point Identification](https://mlsanity.com/paper/1908.10328/) (2019)
- [Finding Blind Spots in Evaluator LLMs with Interpretable Checklists](https://mlsanity.com/paper/2406.13439/) (2024)
- [CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models](https://mlsanity.com/paper/2508.11484/) (2025)
- [Reasoning about Actions and State Changes by Injecting Commonsense Knowledge](https://mlsanity.com/paper/1808.10012/) (2018)
- [FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces](https://mlsanity.com/paper/2501.12909/) (2025)
- [STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative](https://mlsanity.com/paper/2512.12372/) (2025)
- [Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production](https://mlsanity.com/paper/2301.12688/) (2023)
- [Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding](https://mlsanity.com/paper/2109.04947/) (2021)
- [GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography](https://mlsanity.com/paper/2504.07083/) (2025)
- [Taming Camera-Controlled Video Generation with Verifiable Geometry Reward](https://mlsanity.com/paper/2512.02870/) (2025)
- [CinePreGen: Camera Controllable Video Previsualization via Engine-powered Diffusion](https://mlsanity.com/paper/2408.17424/) (2024)
- [CineVision: An Interactive Pre-visualization Storyboard System for Director-Cinematographer Collaboration](https://mlsanity.com/paper/2507.20355/) (2025)
- [The Prose Storyboard Language: A Tool for Annotating and Directing Movies](https://mlsanity.com/paper/1508.07593/) (2015)
- [Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation](https://mlsanity.com/paper/2509.26555/) (2025)
- [ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions](https://mlsanity.com/paper/2512.10286/) (2025)
- [Reviewing Intelligent Cinematography: AI research for camera-based video production](https://mlsanity.com/paper/2405.05039/) (2024)
- [Camera Trajectory Generation: A Comprehensive Survey of Methods, Metrics, and Future Directions](https://mlsanity.com/paper/2506.00974/) (2025)
- [PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualization](https://mlsanity.com/paper/2602.03838/) (2026)

## Abstract (arXiv)

Between a screenplay and a film sits a planning problem that is spatial first: who stands where, and what a camera sees from where it stands. An image diffusion model asked for a shot in free text settles that plan by its own defaults. We present PACE (Precise AI Cinematic Expression), a typed representation for the plan: the screenplay evidence, the characters, props and locations it needs, where each subject stands, and what the camera does. A value is written once at the level it belongs to (script, scene, shot or panel) and inherited below it. A compiler turns the result into both the prompt sent to the diffusion model and a 3D scene built in metres, and a camera solver places the camera so that the declared framing is the framing built. Where a declared value becomes geometry, PACE measures, field by field, how far the compiled camera and the staged render sit from the declaration, rather than asking a model to judge. On the 11-scene Automatic Drive screenplay, every staged single-subject panel places its subject within 1.2% of frame width of its declared position; with two or three subjects one camera pose cannot satisfy every position, and the residual is reported rather than absorbed. On 204 external director-storyboard shots, delivered head height is 1.906 times the staged target from the director's words, 1.733 from the compiled prompt, and 0.955 with the greybox control; the condition that holds framing best draws the described action least. Declaring the pose on 30 shots raises the action drawn from 58.9% to 74.4% without moving the framing. Transitions, fitted motion and human review of the generated panels remain open. Code: https://github.com/StudioPiLabs/pace-core