# CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents

arXiv: https://arxiv.org/abs/2607.26910 · HTML: https://mlsanity.com/paper/2607.26910/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 17 of 17)

- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization](https://mlsanity.com/paper/2201.13360/) (2022)
- [SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences](https://mlsanity.com/paper/2103.14898/) (2021)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://mlsanity.com/paper/2402.04717/) (2024)
- [GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs](https://mlsanity.com/paper/2312.00093/) (2023)
- [GaussNav: Gaussian Splatting for Visual Navigation](https://mlsanity.com/paper/2403.11625/) (2024)
- [E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness](https://mlsanity.com/paper/2407.01516/) (2024)
- [WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents](https://mlsanity.com/paper/2502.15601/) (2025)
- [GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography](https://mlsanity.com/paper/2504.07083/) (2025)
- [ChatCam: Empowering Camera Control through Conversational AI](https://mlsanity.com/paper/2409.17331/) (2024)
- [SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting](https://mlsanity.com/paper/2410.06014/) (2024)
- [Pulp Motion: Framing-aware multimodal camera and human motion generation](https://mlsanity.com/paper/2510.05097/) (2025)
- [LAMP: Language-Assisted Motion Planning for Controllable Video Generation](https://mlsanity.com/paper/2512.03619/) (2025)
- [FOCI: Trajectory Optimization on Gaussian Splats](https://mlsanity.com/paper/2505.08510/) (2025)
- [Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories](https://mlsanity.com/paper/2509.16176/) (2025)

## Built on by (most cited first, 1 of 1)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)

## Abstract (arXiv)

Automatically generating cinematically expressive camera trajectories through 3D scenes from natural language descriptions is a challenging task of high practical value, with applications ranging from real-estate advertising to virtual tour creation. Existing methods either lack true 3D spatial awareness by relying on 2D image priors, or treat trajectory generation as a geometric path planning problem divorced from cinematographic semantics. We present CinemaTraj, a framework that reframes camera trajectory planning as a language-grounded spatial reasoning problem. Given a set of RGB-D images and a user prompt, CinemaTraj equips an LLM agent with a structured 3D scene graph: the agent decomposes the prompt into a sequence of atomic cinematographic movements (dolly, orbit, crane, pan, tilt, zoom, arc). Each movement is instantiated via a novel parametric trajectory representation that is both cinematographically expressive and optimizable for collision avoidance. The scene graph acts as a structured spatial prior, grounding the agent's reasoning in accurate geometric and semantic knowledge of the environment. CinemaTraj further generates synchronized voiceover and subtitles aligned with camera motion, producing narrated cinematic video outputs. We evaluate CinemaTraj on real-world ScanNet++ environments, and show that it produces prompt-faithful, collision-free trajectories with high cinematographic quality, outperforming existing approaches on prompt alignment, trajectory quality, and safety metrics.