ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
This work addresses shape parsing for computer-aided design, enabling editable and interpretable shape representations that integrate with CAD software, though it is an incremental advancement in applying machine learning to reverse engineering.
The paper tackles the problem of learning shapes from point clouds by reverse engineering the sketch-and-extrude modeling process, presenting ExtrudeNet, an unsupervised end-to-end network that outputs compact, editable representations and is the first machine learning approach to do so.
Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning the shape given in the form of point clouds by inverse sketch-and-extrude. We present ExtrudeNet, an unsupervised end-to-end network for discovering sketch and extrude from point clouds. Behind ExtrudeNet are two new technical components: 1) an effective representation for sketch and extrude, which can model extrusion with freeform sketches and conventional cylinder and box primitives as well; and 2) a numerical method for computing the signed distance field which is used in the network learning. This is the first attempt that uses machine learning to reverse engineer the sketch-and-extrude modeling process of a shape in an unsupervised fashion. ExtrudeNet not only outputs a compact, editable and interpretable representation of the shape that can be seamlessly integrated into modern CAD software, but also aligns with the standard CAD modeling process facilitating various editing applications, which distinguishes our work from existing shape parsing research. Code is released at https://github.com/kimren227/ExtrudeNet.