Agents have demonstrated strong capabilities in digital environments, yet their reasoning abilities alone are insufficient to accomplish tasks in the physical world. We present Agentic Aerial Cinematography: From Dialogue Cues to Cinematic Trajectories (ACDC), an agentic framework that bridges this gap for autonomous aerial cinematography. ACDC provides an execution harness that grounds an agent's interpretation of cinematic intent and visual judgment in scene geometry and flight constraints. Given a natural-language request and a 3D scene representation, the agent selects relevant viewpoints and guides their refinement through visual feedback, while optimization and motion planning translate these decisions into executable drone trajectories. Experiments across a variety of simulated indoor scenes and hardware-in-the-loop flight tests demonstrate how this framework connects open-ended user intent to prompt-aligned video tours and physical drone execution.
Figures & tables
Figure 1: The aerial cinematography task addressed by ACDC. Given an underspecified natural-language instruction (left) and a posed exploration video of the scene, ACDC plans an ordered sequence of camera viewpoints and a quadrotor flight path through them. In this restaurant example, the TOGT-optimized trajectory (red) connects 18 selected viewpoints; 12 sampled views are shown and numbered along the top and right.
Figure 2: System overview of ACDC. Given a free-form prompt, a posed exploration video, and a renderable scene ( Inputs ), ACDC operates in three stages: (i) semantic shot planning and seed retrieval (Sec. 3.1 ) grounds VLM-generated shot descriptions in posed exploration frames; (ii) visual preference refinement (Sec. 3.2 ) adjusts each seed’s position and yaw by Bayesian optimization driven by VLM pairwise preferences between rendered views; and (iii) physical trajectory generation (Sec. 3.3 ) connects the refined viewpoints under voxel-map and dynamic constraints.
Figure 3: Semantic shot planning and seed retrieval. A VLM parses the exploration video and instruction into n waypoint descriptions; text and frame embeddings are matched to retrieve up to eight candidate frames per description; the VLM selects and orders a subset of the candidate views, yielding (frame, description, pose) triples.
Figure 4: Qualitative ACDC tours in three simulated scenes (Q1). Columns correspond to the cottage (left), restaurant (middle), and luxury (right) scenes. For each scene, two tours are shown with their prompt summaries and three representative keyframes per tour. Both TOGT-optimized position trajectories are overlaid on each scene at the bottom; thumbnails show the original selected exploration frames.
Aerial robotics studies the design, perception, control, and coordination of flying robots for navigation, inspection, transport, and physical interaction.
Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D environments. To generate these trajectories, a Director agent constructs executable camera plans by composing high-level motions from concurrent atomic operations that jointly control translation, rotation, and framing. The Director is supported by three specialized agents: an Interpreter that extracts scene-grounded cinematographic intent, a Scout that selects initial viewpoints, and a Critic that evaluates rendered results and provides visual feedback for iterative plan refinement. We also introduce CinemaBench, comprising 150 Blender scenes from self-created and licensed sources, with five camera instructions per scene for 750 text-directed tasks and 60 reference videos associated with a subset of scenes. CinemaBench supports evaluation of both text-directed camera generation and video reference-directed camera generation. Across a diverse set of evaluated baselines, FilmFlow achieves the strongest benchmark performance and the highest user preference, demonstrating effective spatial reasoning, temporal coordination, and visual composition for executable 3D cinematography.
Yiming Zhang, Jiarui Guo, Haojia Wei +5
Cornell University · Shanghai Jiao Tong University · University of California, Los Angeles +1
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.
Qianru Li, Xuyang Chen, Erkin Türköz +5
Technical University of Munich Munich, Germany · Huawei Dresden Research Center Munich, Germany
We propose Camera Artist, a multi-agent framework that models a real-world filmmaking workflow to generate narrative videos with explicit cinematic language. While recent multi-agent systems have made substantial progress in automating filmmaking workflows from scripts to videos, they often lack explicit mechanisms to structure narrative progression across adjacent shots and deliberate use of cinematic language, resulting in fragmented storytelling and limited filmic quality. To address this, Camera Artist builds upon established agentic pipelines and introduces a dedicated Cinematography Shot Agent, which integrates recursive storyboard generation to strengthen shot-to-shot narrative continuity and cinematic language injection to produce more expressive, film-oriented shot designs. Extensive quantitative and qualitative results demonstrate that our approach consistently outperforms existing baselines in narrative consistency, dynamic expressiveness, and perceived film quality.
Haobo Hu, Qi Mao, Yuanhang Li +1
School of Information and Communication Engineering, Communication University of China, Beijing, China · State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China