DeepAI AI Chat
Log In Sign Up

UCSG-Net – Unsupervised Discovering of Constructive Solid Geometry Tree

by   Kacper Kania, et al.

Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods that are based on such representation achieved state-of-the-art 3D shape reconstruction quality. However, these methods struggle to reconstruct non-convex shapes. One remedy is to incorporate a constructive solid geometry framework (CSG) that represents a shape as a decomposition into primitives. It allows to embody a 3D shape of high complexity and non-convexity with a simple tree representation of Boolean operations. Nevertheless, existing approaches are supervised and require the entire CSG parse tree that is given upfront during the training process. On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net. Our model predicts parameters of primitives and binarizes their SDF representation through differentiable indicator function. It is achieved jointly with discovering the structure of a Boolean operators tree. The model selects dynamically which operator combination over primitives leads to the reconstruction of high fidelity. We evaluate our method on 2D and 3D autoencoding tasks. We show that the predicted parse tree representation is interpretable and can be used in CAD software.


page 4

page 7

page 13


Neural Shape Parsers for Constructive Solid Geometry

Constructive Solid Geometry (CSG) is a geometric modeling technique that...

A Flexible Pipeline for the Optimization of CSG Trees

CSG trees are an intuitive, yet powerful technique for the representatio...

CSGNet: Neural Shape Parser for Constructive Solid Geometry

We present a neural architecture that takes as input a 2D or 3D shape an...

Finite Boolean Algebras for Solid Geometry using Julia's Sparse Arrays

The goal of this paper is to introduce a new method in computer-aided ge...

CvxNet: Learnable Convex Decomposition

Any solid object can be decomposed into a collection of convex polytopes...

Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly

Representing a 3D shape with a set of primitives can aid perception of s...

On the Complexity of the CSG Tree Extraction Problem

In this short note, we discuss the complexity of the search space for th...

Code Repositories


The official implementation of the "UCSG-Net - Unsupervised Discovering of Constructive Solid Geometry Tree" paper

view repo


Reproducing UCSGNet for CS492 project

view repo