VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
This addresses the challenge of producing visually appealing camera shots in generative camera systems for applications like filmmaking and virtual cinematography, representing a domain-specific advancement.
The paper tackles the problem of generating cinematic camera trajectories that lack visual desirability, such as poor framing and off-screen characters, by introducing VERTIGO, a framework for visual preference optimization. The result is a significant improvement, reducing the character off-screen rate from 38% to nearly 0% while enhancing condition adherence, framing quality, and perceptual realism.
Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned trajectories, but they lack this "director in the loop" and have no explicit supervision of whether a shot is visually desirable. This results in in-distribution camera motion but poor framing, off-screen characters, and undesirable visual aesthetics. In this paper, we introduce VERTIGO, the first framework for visual preference optimization of camera trajectory generators. Our framework leverages a real-time graphics engine (Unity) to render 2D visual previews from generated camera motion. A cinematically fine-tuned vision-language model then scores these previews using our proposed cyclic semantic similarity mechanism, which aligns renders with text prompts. This process provides the visual preference signals for Direct Preference Optimization (DPO) post-training. Both quantitative evaluations and user studies on Unity renders and diffusion-based Camera-to-Video pipelines show consistent gains in condition adherence, framing quality, and perceptual realism. Notably, VERTIGO reduces the character off-screen rate from 38% to nearly 0% while preserving the geometric fidelity of camera motion. User study participants further prefer VERTIGO over baselines across composition, consistency, prompt adherence, and aesthetic quality, confirming the perceptual benefits of our visual preference post-training.