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

• URL: http://arxiv.org/abs/2607.26910v1
• Date: Wed, 29 Jul 2026 13:41:52 GMT
• Title: CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents
• Abstract summary: CinemaTraj is a framework that reframes camera trajectory planning as a language-grounded spatial reasoning problem.<n>It produces prompt-faithful, collision-free trajectories with high cinematographic quality.
• Score: 14.879115975370842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation [48.49793109378558]
  We present Auteur, a method for language-driven, human-centric camera framing in generative video.<n>Auteur enables cinematographic framing of human-centered scenes, a capability largely absent in prior generative models.
  arXiv  Detail & Related papers  (2026-06-01T08:41:01Z)
• SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens [89.05195827071582]
  SceMoS is a scene-aware motion synthesis framework.<n>It disentangles global planning from local execution using lightweight 2D cues.<n>SceMoS achieves state-of-the-art motion realism and contact accuracy on the TRUMANS benchmark.
  arXiv  Detail & Related papers  (2026-02-24T02:09:12Z)
• CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation [65.03946626081036]
  We present CineScene, a framework that leverages implicit 3D-aware scene representation for cinematic video generation.<n>CineScene achieves state-of-the-art performance in scene-consistent cinematic video generation.
  arXiv  Detail & Related papers  (2026-02-06T18:59:24Z)
• RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming [79.81527946524098]
  RoamScene3D is a novel framework that bridges the gap between semantic guidance and spatial generation.<n>We employ a vision-language model (VLM) to construct a scene graph that encodes object relations.<n>To mitigate the limitations of static 2D priors, we introduce a Motion-Injected Inpainting model that is fine-tuned on a synthetic panoramic dataset.
  arXiv  Detail & Related papers  (2026-01-27T10:10:55Z)
• HouseTour: A Virtual Real Estate A(I)gent [80.36635722117329]
  We introduce HouseTour, a method for spatially-aware 3D camera trajectory and natural language summary generation.<n>Our approach generates smooth video trajectories via a diffusion process constrained by known camera poses.<n>We synthesize the final video using 3D Gaussian splatting to render novel views along the trajectory.
  arXiv  Detail & Related papers  (2025-10-20T19:47:35Z)
• CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation [76.72787726497343]
  We present CineMaster, a framework for 3D-aware and controllable text-to-video generation.<n>Our goal is to empower users with comparable controllability as professional film directors.
  arXiv  Detail & Related papers  (2025-02-12T18:55:36Z)
• Cinematic Behavior Transfer via NeRF-based Differentiable Filming [63.1622492808519]
  Existing SLAM methods face limitations in dynamic scenes and human pose estimation often focuses on 2D projections. We first introduce a reverse filming behavior estimation technique. We then introduce a cinematic transfer pipeline that is able to transfer various shot types to a new 2D video or a 3D virtual environment.
  arXiv  Detail & Related papers  (2023-11-29T15:56:58Z)
• Automatic Camera Trajectory Control with Enhanced Immersion for Virtual Cinematography [23.070207691087827]
  Real-world cinematographic rules show that directors can create immersion by comprehensively synchronizing the camera with the actor. Inspired by this strategy, we propose a deep camera control framework that enables actor-camera synchronization in three aspects. Our proposed method yields immersive cinematic videos of high quality, both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2023-03-29T22:02:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.