Sketching with Style: Visual Search with Sketches and Aesthetic Context
Sketching with Style: Visual Search with Sketches and Aesthetic Context
复制标题
DOI：
10.1109/iccv.2017.290
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
J. Collomosse;Tu Bui;Michael J. Wilber;Chen Fang;Hailin Jin
中科院分区：
文献类型：
--
作者：
J. Collomosse;Tu Bui;Michael J. Wilber;Chen Fang;Hailin Jin
我们提出了一种新的视觉相似性的图像检索，结合结构和美学（风格）的限制措施。我们的算法接受一个查询作为草图形状，和一组一个或多个上下文图像指定所需的视觉美学。三元组网络用于学习能够独立于结构测量风格相似性的特征嵌入，与以前的风格识别网络相比，具有显着的增益。我们将这个模型纳入一个分层的三元组网络中，以统一和学习来自两个有区别的训练流的风格和结构的联合空间。我们证明，这个空间使，第一次，stylecconstrained草图搜索在一个不同的域的数字艺术品，包括图形，绘画和素描。我们还简要探讨了替代查询方式。
We propose a novel measure of visual similarity for image retrieval that incorporates both structural and aesthetic (style) constraints. Our algorithm accepts a query as sketched shape, and a set of one or more contextual images specifying the desired visual aesthetic. A triplet network is used to learn a feature embedding capable of measuring style similarity independent of structure, delivering significant gains over previous networks for style discrimination. We incorporate this model within a hierarchical triplet network to unify and learn a joint space from two discriminatively trained streams for style and structure. We demonstrate that this space enables, for the first time, styleconstrained sketch search over a diverse domain of digital artwork comprising graphics, paintings and drawings. We also briefly explore alternative query modalities.