SAGE：基于归因引导规则演化的自演进分镜脚本技能
SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution
浏览论文内容
中文总结 AI 辅助
针对分镜脚本制作的工业瓶颈，提出SAGE框架，通过归因引导规则演化实现导演知识的自演进，在测试中表现接近专业导演，部署后大幅提升制作效率，还发布了首个相关公开数据集PROSE
中文摘要 AI 辅助
分镜脚本将剧本转化为自动制作短剧的视觉镜头计划，专业分镜脚本制作依赖隐性导演专业知识，仍是工业瓶颈。大语言模型可实现该步骤自动化，但注入导演知识的方法面临三大挑战：（1）知识获取：该技艺隐含于示例中，或需手动编写；（2）知识提炼：编写的知识未依据执行结果评估，且不透明的生成过程无法将反馈归因于每项决策背后的知识；（3）知识注入：注入所有知识会超出可用上下文，而针对每个叙事组手动选择知识无法规模化。本文提出SAGE（Skill with Attribution-Guided Evolution，归因引导演化技能），这是一个从专家演示中学习、归因、演化和路由导演知识的部署框架。SAGE通过对比每个训练剧本与其专家分镜脚本，推导独立于剧集内容的规则。生成过程中，模型记录每个叙事组采用的规则，将这些记录与局部反馈结合，可对单个规则进行针对性更新。演化后的规则形成带路由索引的场景包，使每个组无需专家干预即可仅检索与其场景适配的有限规则集。在涵盖三种类型的18个测试剧集上，SAGE在经专家验证的评分标准中得分为77.8，而专业导演的得分为77.1。SAGE在虚拟电影工作室（Virtual Film Studio）部署14天，生成1344个叙事组输出，其中87.2%无需实质性编辑即可被接受，制作团队记录的每集创作时间减少了83%以上。本文发布了PROSE，这是首个公开的包含68集剧本与专业导演分镜脚本配对的数据集：this https URL
英文摘要
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.
发表机构
- Shanghai Jiao Tong University（上海交通大学）
- CreativeFitting（创意拟合）
机构由 AI 辅助整理，请以论文原文为准。
