A Survey of Methods for Converting Unstructured Data to CSG Models

Abstract

The goal of this document is to survey existing methods for recovering CSG representations from unstructured data such as 3D point-clouds or polygon meshes. We review and discuss related topics such as the segmentation and fitting of the input data. We cover techniques from solid modeling and CAD for polyhedron to CSG and B-rep to CSG conversion. We look at approaches coming from program synthesis, evolutionary techniques (such as genetic programming or genetic algorithm), and deep learning methods. Finally, we conclude with a discussion of techniques for the generation of computer programs representing solids (not just CSG models) and higher-level representations (such as, for example, the ones based on sketch and extrusion or feature based operations).

29 pages

References in corpus (12)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Combinatorial Optimization with Physics-Inspired Graph Neural Networks
• Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey
• ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis
• Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields
• Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds
• Computer-Aided Design as Language
• Fit4CAD: A point cloud benchmark for fitting simple geometric primitives in CAD objects
• ShapeMOD: Macro Operation Discovery for 3D Shape Programs
• Accelerating Evolutionary Construction Tree Extraction via Graph Partitioning
• PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
• A Flexible Pipeline for the Optimization of CSG Trees