让视频叙事更连贯，自动规划角色与场景一致性。
CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding
- 用多智能体协同规划故事板，确保角色和背景一致。
- 在三个基准上提升21.6%背景连续性、9.6%角色一致性。
- 适合需要长序列视觉连贯性的生成任务，如动画创作。
长时序视觉叙事需保持镜头间的连续性，包括角色一致性、环境稳定性和场景过渡自然。现有生成模型虽能产出高质量单帧图像，但难以维持这种连续性，导致角色外观变化、背景不一致或场景突变。本文提出CANVAS（基于视觉代理分镜的故事连续性框架），一个通过角色连续性、持久背景锚点和位置感知场景规划来显式建模视觉连续性的多智能体系统。我们在两个分镜生成基准ST-BENCH和ViStoryBench上评估该方法，并引入新的挑战性基准HardContinuityBench以测试长程叙事一致性。实验表明，CANVAS持续优于最强基线，在背景连续性上提升21.6%，角色一致性提升9.6%，道具一致性提升7.6%。
原文摘要 · Abstract (English)
Long-form visual storytelling requires maintaining continuity across shots, including consistent characters, stable environments, and smooth scene transitions. While existing generative models can produce strong individual frames, they fail to preserve such continuity, leading to appearance changes, inconsistent backgrounds, and abrupt scene shifts. We introduce CANVAS (Continuity-Aware Narratives via Visual Agentic Storyboarding), a multi-agent framework that explicitly plans visual continuity in multi-shot narratives. CANVAS enforces coherence through character continuity, persistent background anchors, and location-aware scene planning for smooth transitions within the same setting We evaluate CANVAS on two storyboard generation benchmarks ST-BENCH and ViStoryBench and introduce a new challenging benchmark HardContinuityBench for long-range narrative consistency. CANVAS consistently outperforms the best-performing baseline, improving background continuity by 21.6%, character consistency by 9.6% and props consistency by 7.6%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。