# LensCraft: Your Professional Virtual Cinematographer

arXiv: https://arxiv.org/abs/2506.00988 · HTML: https://mlsanity.com/paper/2506.00988/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 19 of 19)

- [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)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text](https://mlsanity.com/paper/2406.17601/) (2024)
- [ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching](https://mlsanity.com/paper/1709.01215/) (2017)
- [E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness](https://mlsanity.com/paper/2407.01516/) (2024)
- [ChatCam: Empowering Camera Control through Conversational AI](https://mlsanity.com/paper/2409.17331/) (2024)
- [Cinematic Behavior Transfer via NeRF-based Differentiable Filming](https://mlsanity.com/paper/2311.17754/) (2023)
- [The Prose Storyboard Language: A Tool for Annotating and Directing Movies](https://mlsanity.com/paper/1508.07593/) (2015)
- [Directing Cinematographic Drones](https://mlsanity.com/paper/1712.04216/) (2017)
- [Batteries, camera, action! Learning a semantic control space for expressive robot cinematography](https://mlsanity.com/paper/2011.10118/) (2020)
- [Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming](https://mlsanity.com/paper/1808.09563/) (2018)
- [Optimizing for Aesthetically Pleasing Quadrotor Camera Motion](https://mlsanity.com/paper/1906.11686/) (2019)

## Built on by (most cited first, 2 of 2)

- [CineLOG: A Training Free Approach for Cinematic Long Video Generation](https://mlsanity.com/paper/2512.12209/) (2025)
- [PACE: Precise AI Cinematic Expression](https://mlsanity.com/paper/2609.19853/) (2026)

## Abstract (arXiv)

Digital creators, from indie filmmakers to animation studios, face a persistent bottleneck: translating their creative vision into precise camera movements. Despite significant progress in computer vision and artificial intelligence, current automated filming systems struggle with a fundamental trade-off between mechanical execution and creative intent. Crucially, almost all previous works simplify the subject to a single point-ignoring its orientation and true volume-severely limiting spatial awareness during filming. LensCraft solves this problem by mimicking the expertise of a professional cinematographer, using a data-driven approach that combines cinematographic principles with the flexibility to adapt to dynamic scenes in real time. Our solution combines a specialized simulation framework for generating high-fidelity training data with an advanced neural model that is faithful to the script while being aware of the volume and dynamic behavior of the subject. Additionally, our approach allows for flexible control via various input modalities, including text prompts, subject trajectory and volume, key points, or a full camera trajectory, offering creators a versatile tool to guide camera movements in line with their vision. Leveraging a lightweight real time architecture, LensCraft achieves markedly lower computational complexity and faster inference while maintaining high output quality. Extensive evaluation across static and dynamic scenarios reveals unprecedented accuracy and coherence, setting a new benchmark for intelligent camera systems compared to state-of-the-art models. Extended results, the complete dataset, simulation environment, trained model weights, and source code are publicly accessible on LensCraft Webpage.