Finding point‐wise correspondences between images is a long‐standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper, we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non‐photorealistic rendering over a large collection of part‐based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown togeneralize correctly in unseen sketches hand‐drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication.

中文翻译：

---

SketchZooms：用于匹配线图的深层多视图描述符

在图像分析中寻找图像之间的逐点对应关系是一个长期存在的问题。由于人类绘画风格的变化，投影变形和视口变化，这对于素描图像而言尤其具有挑战性。在本文中，我们提出了首次尝试获取用于线图中密集注册的学习描述符。基于最近针对相应照片的深度学习技术，我们设计了描述符来局部匹配图像对，其中感兴趣的对象属于相同的语义类别，但形状，形式和投影角度仍然大不相同。为此，我们专门针对大量基于零件的已注册3D模型，使用非真实感渲染精心制作了合成草图的数据集。训练结束后，神经网络为输入图像中的每个像素生成描述符，这些描述符在人工绘制的看不见的草图中已正确概括。除了与已在草图中证明有效的其他描述符进行比较之外，我们还根据专家设计人员收集的通信数据的基线来评估我们的方法。代码，数据和其他资源将在发布时公开发布。