CANVAS: computer-assisted narrative animation synthesis
CANVAS: computer-assisted narrative animation synthesis
复制标题
CANVAS：计算机辅助叙事动画合成
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
M. Gross
中科院分区：
文献类型：
--
作者：
Mubbasir Kapadia;Seth Frey;Alexander Shoulson;R. Sumner;M. Gross
尽管动画表现性虚拟角色的解决方案已经成熟，但实现故事作者创作意图的创新还没有取得同样的进展。关键的挑战是为故事创作提供一个可访问的，但富有表现力的界面，使叙事概念的快速原型化，迭代和部署成为可能。我们提出CANVAS，一个计算机辅助视觉创作工具，用于从稀疏指定的叙事事件合成多角色动画。在一个类似于故事板的过程中，作者在故事中布局关键情节点，我们的系统自动填充缺失的细节，以合成符合作者约束的3D动画。艺术家和导演可以使用CANVAS以迭代的方式预先可视化故事板，临时用户可以提供任意稀疏的规范和利用自动化来快速生成不同的叙述。CANVAS提供了一个可访问的界面，用于快速创作和预先可视化复杂的叙述。自动化进一步减少了创作工作，而不会破坏创作控制或干扰讲故事的过程。
Despite the maturity in solutions for animating expressive virtual characters, innovations realizing the creative intent of story writers have yet to make the same strides. The key challenge is to provide an accessible, yet expressive interface for story authoring that enables the rapid prototyping, iteration, and deployment of narrative concepts. We present CANVAS, a computer-assisted visual authoring tool for synthesizing multi-character animations from sparsely-specified narrative events. In a process akin to storyboarding, authors lay out the key plot points in a story, and our system automatically fills in the missing details to synthesize a 3D animation that meets author constraints. CANVAS can be used by artists and directors to pre-visualize storyboards in an iterative fashion, and casual users may provide arbitrarily sparse specifications and harness automation to rapidly generate diverse narratives. CANVAS provides an accessible interface for rapidly authoring and pre-visualizing complex narratives. Automation reduces the authoring effort further without undermining creative control or interfering with the storytelling process.