Molecumentary：使用分子可视化的可扩展旁白纪录片
Molecumentary: Scalable Narrated Documentaries Using Molecular Visualization
AI总结：
提出一种基于实时分子可视化的可扩展纪录片制作方法，通过构建故事图并生成虚拟导览与语音旁白，合成具有专业解说的分子纪录片。
摘要：
我们提出了一种使用实时科学可视化制作纪录片风格内容的方法。我们制作了molecumentaries，即以分子生物学结构模型为特色的分子纪录片。我们采用可扩展的方法，而非僵化的传统制作流程。我们方法的动机在于交互式科学可视化的快速发展，这在科学传播中展现出巨大潜力。然而，如果没有某种形式的解释或指导，新手和非专业人士通常很难从可视化本身获得洞察。我们通过语音通道整合此类知识，并将其与引人入胜的视觉呈现一起提供。为实现molecumentary的合成，我们提供了两个主要制作步骤的技术解决方案：1）准备故事结构，以及2）将故事转化为具体叙事。在第一步中，来自异构来源的关于模型的信息被编译成故事图。本地知识与远程来源相结合，以完成故事图并丰富最终结果。在第二步中，使用故事图合成叙事，即按顺序呈现的故事元素。我们提出了一种遍历故事图并生成虚拟导览的方法，使用自动化相机和可视化过渡。由领域专家撰写的文本通过文本转语音功能转换为语音表示，并作为旁白提供。使用所描述的框架，我们合成了带有描述的自动飞越，模仿手动制作的纪录片。此外，我们展示了第二个场景：通过文本输入引导纪录片叙事。
英文摘要：
We present a method for producing documentary-style content using real-time scientific visualization. We produce molecumentaries, i.e., molecular documentaries featuring structural models from molecular biology. We employ scalable methods instead of the rigid traditional production pipeline. Our method is motivated by the rapid evolution of interactive scientific visualization, which shows great potential in science dissemination. Without some form of explanation or guidance, however, novices and lay-persons often find it difficult to gain insights from the visualization itself. We integrate such knowledge using the verbal channel and provide it along an engaging visual presentation. To realize the synthesis of a molecumentary, we provide technical solutions along two major production steps: 1) preparing a story structure and 2) turning the story into a concrete narrative. In the first step, information about the model from heterogeneous sources is compiled into a story graph. Local knowledge is combined with remote sources to complete the story graph and enrich the final result. In the second step, a narrative, i.e., story elements presented in sequence, is synthesized using the story graph. We present a method for traversing the story graph and generating a virtual tour, using automated camera and visualization transitions. Texts written by domain experts are turned into verbal representations using text-to-speech functionality and provided as a commentary. Using the described framework we synthesize automatic fly-throughs with descriptions that mimic a manually authored documentary. Furthermore, we demonstrate a second scenario: guiding the documentary narrative by a textual input.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
