Learning Cuboid Abstraction of 3D Shapes via Iterative Error Feedback. (December 2021)

• Record Type: Journal Article
• Authors: Zhao, Xi; Wang, Haoran; Zhang, Bowen; Yang, Yi-Jun; Hu, Ruizhen
• Is Part Of: Computer aided design. Volume 141(2021)
• Publication Date: 2021-12
• Subjects: Abstraction -- Primitives -- Iterative error feedback -- Regression -- Deep learning; Computer-aided design -- Periodicals; Engineering design -- Data processing -- Periodicals; Computer graphics -- Periodicals; Conception technique -- Informatique -- Périodiques; Infographie -- Périodiques; Computer graphics; Engineering design -- Data processing; Periodicals; Electronic journals; 620.00420285
• DOI: 10.1016/j.cad.2021.103092
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: Abstracting human-made 3D models by a set of primitives, such as cuboid abstraction, is a fundamental task in 3D shape modelling and analysis. Traditionally, different forms of representations, such as edges, volumes, or curves, were used as primitives. Although methods that apply local operations to compute such primitives can produce satisfactory results with their own merits, the computations can be very slow with complex models. Learning-based abstraction methods are much faster but cannot guarantee the fitting precision between the primitives and the original shape. To solve this problem, we propose an unsupervised learning approach for shape abstraction. Our method's key idea is to use an iterative error feedback (IEF)-based network to improve primitive precision. Our method contains two main steps. First, we use a regression network to predict the initial primitives. Second, we increase the accuracy of the initial primitives by using an IEF-based network, which iteratively outputs the primitive updates. We demonstrate the advantages of our method by comparing it to existing state-of-the-art methods. We also thoroughly evaluate our method by ablation studies. Highlights: We propose a newly developed unsupervised learning method for 3D shape abstraction. The key of our method is a novel iterative error feedback based network. Our method can improve the accuracy of the abstraction results. We conduct an extensive evaluation of the proposed method.