ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing

TL;DR

ExtrudeNet is an unsupervised neural network that learns to reverse engineer 3D shapes into sketch and extrude representations, enabling editable CAD-compatible models from point clouds.

Contribution

This work introduces the first unsupervised machine learning approach for inverse sketch-and-extrude shape parsing, with novel representations and a signed distance field computation method.

Findings

Successfully recovers sketch and extrude parameters from point clouds

Produces compact, editable, and CAD-compatible shape representations

Outperforms existing methods in shape parsing accuracy

Abstract

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.