Doodle2App: Native App Code by Freehand UI Sketching
Doodle2App: Native App Code by Freehand UI Sketching
复制标题
DOI：
10.1145/3387905.3388607
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Soumik Mohian-;Christoph Csallner
中科院分区：
文献类型：
--
作者：
Soumik Mohian-;Christoph Csallner
用户界面开发通常从徒手素描开始，纸上的笔在软件开发过程中造成了很大的差距。在大型草图中风序列中训练的深神经网络中的最新进展已实现了在线草图检测，该检测支持许多以高分类精度的草图元素类。本文利用了最近的Google快速绘画！ 50m草图中风序列的数据集，以预先培训复发性神经网络，并使用我们通过亚马逊机械Turk收集的草图中风序列对其进行了重新训练。由此产生的doodle2app网站提供了纸质替代品，即带有Interactive UI预览的绘图接口，可以将草图转换为可编译的单页Android应用程序。在712个草图样品上，doodle2app比最先进的工具传送的准确性更高。视频演示在https://youtu.be/p4sb0pktney上
User interface development typically starts with freehand sketching, with pen on paper, which creates a big gap in the software development process. Recent advances in deep neural networks that have been trained on large sketch stroke sequence collections have enabled online sketch detection that supports many sketch element classes at high classification accuracy. This paper leverages the recent Google Quick, Draw! dataset of 50M sketch stroke sequences to pre-train a recurrent neural network and retrains it with sketch stroke sequences we collected via Amazon Mechanical Turk. The resulting Doodle2App website offers a paper substitute, i.e., a drawing interface with interactive UI preview and can convert sketches to a compilable single-page Android application. On 712 sketch samples Doodle2App achieved higher accuracy than the state-of-the-art tool Teleport. A video demo is at https://youtu.be/P4sb0pKTNEY