Differentiable 3D CAD Programs for Bidirectional Editing

TL;DR

This paper presents a differentiable, bidirectional editing system for 3D CAD programs that allows users to intuitively modify designs by directly manipulating geometry or parameters, with the system inferring updates to maintain consistency.

Contribution

It introduces a novel differentiable CAD programming language and inverse editing framework enabling seamless, interactive shape editing and parameter inference in complex 3D models.

Findings

Enables rapid, interactive design exploration with consistent geometry and parameters.

Supports complex 3D models with many parameters for diverse design variants.

Demonstrates effective inverse editing without explicit topology optimization.

Abstract

Modern CAD tools represent 3D designs not only as geometry, but also as a program composed of geometric operations, each of which depends on a set of parameters. Program representations enable meaningful and controlled shape variations via parameter changes. However, achieving desired modifications solely through parameter editing is challenging when CAD models have not been explicitly authored to expose select degrees of freedom in advance. We introduce a novel bidirectional editing system for 3D CAD programs. In addition to editing the CAD program, users can directly manipulate 3D geometry and our system infers parameter updates to keep both representations in sync. We formulate inverse edits as a set of constrained optimization objectives, returning plausible updates to program parameters that both match user intent and maintain program validity. Our approach implements an automatically differentiable domain-specific language for CAD programs, providing derivatives for this optimization to be performed quickly on any expressed program. Our system enables rapid, interactive exploration of a constrained 3D design space by allowing users to manipulate the program and geometry interchangeably during design iteration. While our approach is not designed to optimize across changes in geometric topology, we show it is expressive and performant enough for users to produce a diverse set of design variants, even when the CAD program contains a large number of parameters.