🤖 AI Summary
This study addresses the challenge that generative video reshoots, which require hallucinating unrecorded content, prevent on-set real-time risk awareness. We propose a hybrid cinematography workflow integrating 3D editable shot planning, video proxy techniques, a mobile augmented reality application, and an offline processing pipeline. This framework enables, for the first time, real-time pre-visualization assessment and interactive adjustment of hallucination risks in generative reshoots prior to filming. Our findings demonstrate that risk pre-visualization effectively optimizes camera decision-making while revealing the inherent tension between creative intent and generative hallucination. Ultimately, this work establishes a novel paradigm for safe and controllable AI-assisted film production.
📝 Abstract
On a film set, the camera move is committed during a take. Generative video reshooting lets filmmakers change it afterward, but may require hallucinating unrecorded content, a gap sometimes discovered only after leaving the set. We present Hybrid Cinematography, a workflow that bridges physical capture and generative reshooting to manage hallucination risk while filmmakers can still act on it. Using an editable 3D shot plan and a proxy of the take, our previsualization evaluates hallucination risk in real time. Seeing where the take lacks support, filmmakers can iteratively adjust the plan, explore moves that balance capture and generation, shoot guided pickups, or knowingly accept hallucination. We demonstrate the workflow through a mobile augmented reality application for on-set planning, capture, and review, and an offline pipeline for existing video. A study with experienced filmmakers reveals how previsualizing risk informs camera decisions and exposes tensions between creative intent and generative hallucination.