SAGE让AI自动学习导演经验，自动生成可优化的分镜方案。
SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution
- 通过对比剧本与分镜，自动提炼不依赖内容的导演规则。
- 在生成中记录规则使用，结合反馈精准更新单条规则。
- 规则打包并智能路由，适合大规模自动化短剧生产。
分镜是将剧本转化为视觉镜头计划的关键步骤，依赖导演隐性经验，已成为自动化短剧制作的瓶颈。尽管大语言模型可辅助此过程，但获取、精炼和注入导演知识面临三大挑战：（1）知识获取难，技艺隐含于范例或需手动编写；（2）知识难以评估，生成过程不透明，无法追溯决策背后的依据；（3）知识注入受限，全部注入超出上下文容量，逐项人工选择又无法扩展。我们提出SAGE（基于归因引导的规则演化技能），一个可部署框架，能从专家示范中学习、归因、演化并调度导演知识。SAGE通过对比每个训练剧本与其专家分镜，提取独立于剧情内容的规则。生成时，模型记录各叙事组采纳的规则，并结合局部反馈实现规则的精准更新。演化后的规则组成场景包并附带路由索引，使每组仅调用适配的有限规则，无需人工干预。在三个类型共18个测试剧集中，SAGE评分77.8，略高于专业导演的77.1。在虚拟电影工作室部署14天内，生成1344个叙事组输出，87.2%无需实质性修改，制作团队每集撰写时间减少超83%。我们发布首个公开数据集PROSE，包含68部专业导演的剧本-分镜对，地址：https://github.com/creDreams/PROSE。
原文摘要 · Abstract (English)
Storyboards turn screenplays into visual shot plans for automated short drama production. Professional storyboarding relies on tacit directorial expertise and remains an industrial bottleneck. Large language models can automate this step, but methods for supplying directing knowledge face three challenges: (1) Knowledge acquisition: the craft remains implicit in exemplars or must be written manually. (2) Knowledge refinement: authored knowledge is not evaluated against execution outcomes, and opaque generation prevents feedback attribution to the knowledge behind each decision. (3) Knowledge injection: injecting all knowledge exceeds usable context, while manual selection for every narrative group does not scale. We present SAGE (Skill with Attribution-Guided Evolution), a deployed framework that learns, attributes, evolves, and routes directing knowledge from expert demonstrations. SAGE derives rules that are independent of episode content by contrasting each training screenplay with its expert storyboard. During generation, the model records each narrative group's adopted rules. Combining these records with localized feedback enables targeted updates to individual rules. Evolved rules form scenario packages with a routing index, so each group retrieves only a bounded set appropriate to its situation without expert intervention. On 18 test episodes across three genres, SAGE scored 77.8 on a rubric validated by experts, versus 77.1 for professional directors. Deployed for 14 days on Virtual Film Studio, SAGE produced 1,344 narrative group outputs; 87.2 percent were accepted without substantive edits, and the production team recorded over 83 percent less authoring time per episode. We release PROSE, the first public dataset pairing screenplays with storyboards by professional directors across 68 episodes: https://github.com/creDreams/PROSE.
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。