2021/05/06 by Yaroslav Ganin, Ganin, Yaroslav, Sergey Bartunov +8 · 1 voice · 41 citations
Computer Science · Engineering · #Algorithm #Artificial intelligence #CAD #Component (thermodynamics) #Computer Aided Design #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain (mathematical analysis) #Engineering #Engineering drawing #FOS: Computer and information sciences #Flexibility (engineering) #Generative Adversarial Networks and Image Synthesis #Handwritten Text Recognition Techniques #Human–computer interaction #Image Processing and 3D Reconstruction #Machine Learning (cs.LG) #Perspective (graphical) #Programming language #Protocol (science) #Serialization #Sketch #Software engineering #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2105.02769
published in arXiv (Cornell University) (Cornell University) · 24 pages, 11 figures, 3 tables
arxiv created 2021/05/06 · openalex publication_date 2021/05/06 · arxiv published 2021/05/06 · arxiv updated 2021/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Computer-Aided Design (CAD) applications are used in manufacturing to model everything from coffee mugs to sports cars. These programs are complex and require years of training and experience to master. A component of all CAD models particularly difficult to make are the highly structured 2D sketches that lie at the heart of every 3D construction. In this work, we propose a machine learning model capable of automatically generating such sketches. Through this, we pave the way for developing intelligent tools that would help engineers create better designs with less effort. Our method is a combination of a general-purpose language modeling technique alongside an off-the-shelf data serialization protocol. We show that our approach has enough flexibility to accommodate the complexity of the domain and performs well for both unconditional synthesis and image-to-sketch translation.