ChatCam: Empowering Camera Control through Conversational AI

TL;DR

ChatCam leverages conversational AI and a GPT-based model to enable intuitive, language-guided camera control for cinematic video creation, bridging AI perception with professional filmmaking workflows.

Contribution

Introduces ChatCam, a novel system combining language models and camera trajectory tools for natural language-driven camera control in video production.

Findings

Effective interpretation of complex user instructions.

Comparable or superior performance to state-of-the-art methods.

Positive user study feedback on usability and accuracy.

Abstract

Cinematographers adeptly capture the essence of the world, crafting compelling visual narratives through intricate camera movements. Witnessing the strides made by large language models in perceiving and interacting with the 3D world, this study explores their capability to control cameras with human language guidance. We introduce ChatCam, a system that navigates camera movements through conversations with users, mimicking a professional cinematographer's workflow. To achieve this, we propose CineGPT, a GPT-based autoregressive model for text-conditioned camera trajectory generation. We also develop an Anchor Determinator to ensure precise camera trajectory placement. ChatCam understands user requests and employs our proposed tools to generate trajectories, which can be used to render high-quality video footage on radiance field representations. Our experiments, including comparisons to state-of-the-art approaches and user studies, demonstrate our approach's ability to interpret and execute complex instructions for camera operation, showing promising applications in real-world production settings.