Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of approximating a raster or waypoint based stroke encoded as a point-cloud with a variable-degree Bézier curve. Building on this module, we present Cloud2Curve, a generative model for scalable high-resolution vector sketches that can be trained end-to-end using point-cloud data alone. As a consequence, our model is also capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high-resolution scalable Bézier equivalent. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and K-MNIST datasets.
Parametric Primitive Analysis of CAD Sketches with Vision Transformer
College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）；Beihang University（北京航空航天大学）；National University of Defense Technology（国防科技大学）
Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
Beihang University（北航大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Wuhan University（武汉大学）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）
Neural Image Abstraction Using Long Smoothing B-Splines
Goldsmiths, University of London（伦敦大学金史密斯学院）；University of Konstanz（康斯坦茨大学）；Idiap Research Institute（Idiap研究机构）；Reichman University（雷赫利亚大学）；Institute for Clarity in Documentation（文档清晰研究所）；Inria Paris-Rocquencourt（巴黎-罗克奎恩特研究所）；Rajiv Gandhi University（拉贾夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒研究中心）
