# Unveiling the Value of Motion for Cinematic Camera Trajectories

arXiv: https://arxiv.org/abs/2609.38683 · HTML: https://mlsanity.com/paper/2609.38683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 38 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens](https://mlsanity.com/paper/2410.13863/) (2024)
- [TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models](https://mlsanity.com/paper/2503.05638/) (2025)
- [Condensed Movies: Story Based Retrieval with Contextual Embeddings](https://mlsanity.com/paper/2005.04208/) (2020)
- [GIVT: Generative Infinite-Vocabulary Transformers](https://mlsanity.com/paper/2312.02116/) (2023)
- [Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text](https://mlsanity.com/paper/2406.17601/) (2024)
- [MarDini: Masked Autoregressive Diffusion for Video Generation at Scale](https://mlsanity.com/paper/2410.20280/) (2024)
- [A Unified Framework for Shot Type Classification Based on Subject Centric Lens](https://mlsanity.com/paper/2008.03548/) (2020)
- [Taming Teacher Forcing for Masked Autoregressive Video Generation](https://mlsanity.com/paper/2501.12389/) (2025)
- [E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness](https://mlsanity.com/paper/2407.01516/) (2024)
- [CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation](https://mlsanity.com/paper/2505.15145/) (2025)
- [ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models](https://mlsanity.com/paper/2506.21356/) (2025)
- [Cinematographic Camera Diffusion Model](https://mlsanity.com/paper/2402.16143/) (2024)
- [GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography](https://mlsanity.com/paper/2504.07083/) (2025)
- [Learning Camera Movement Control from Real-World Drone Videos](https://mlsanity.com/paper/2412.09620/) (2024)

## Abstract (arXiv)

Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves in terms of direction and speed. Recent work on camera trajectory generation and alignment to text relies on pose-centric representations. While in principle a network could derive direction of movement and speed, we find that in practice this might not happen. In fact, in this paper we discover that decomposing the camera trajectory representation from the traditional per-frame poses to direction and speed has surprising benefits across multiple tasks, including trajectory-to-text alignment as well as text-to-trajectory generation. To accurately evaluate the former, we introduce a simple and reliable protocol that overcomes the limitations of prior evaluation baselines. For the latter, building on this representational insight, we propose a novel generative model for camera trajectories, CineGEN, that achieves superior performance across a variety of metrics. We also propose a novel dataset, CineScript, containing movie clips that are enriched with scene descriptions as well as higher-level metadata. This novel data allows us to test models' ability to capture high-level cinematographic information. We show that, despite its simplicity, representing camera trajectories through direction and speed not only helps numerically to achieve better alignment and generation, but also inherently encodes complex directorial intent.