Timezone: »

 
Poster
SketchGen: Generating Constrained CAD Sketches
Wamiq Para · Shariq Bhat · Paul Guerrero · Tom Kelly · Niloy Mitra · Leonidas Guibas · Peter Wonka

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

Computer-aided design (CAD) is the most widely used modeling approach for technical design. The typical starting point in these designs is 2D sketches which can later be extruded and combined to obtain complex three-dimensional assemblies. Such sketches are typically composed of parametric primitives, such as points, lines, and circular arcs, augmented with geometric constraints linking the primitives, such as coincidence, parallelism, or orthogonality. Sketches can be represented as graphs, with the primitives as nodes and the constraints as edges. Training a model to automatically generate CAD sketches can enable several novel workflows, but is challenging due to the complexity of the graphs and the heterogeneity of the primitives and constraints. In particular, each type of primitive and constraint may require a record of different size and parameter types.We propose SketchGen as a generative model based on a transformer architecture to address the heterogeneity problem by carefully designing a sequential language for the primitives and constraints that allows distinguishing between different primitive or constraint types and their parameters, while encouraging our model to re-use information across related parameters, encoding shared structure. A particular highlight of our work is the ability to produce primitives linked via constraints that enables the final output to be further regularized via a constraint solver. We evaluate our model by demonstrating constraint prediction for given sets of primitives and full sketch generation from scratch, showing that our approach significantly out performs the state-of-the-art in CAD sketch generation.

Keywords: Transformers · Generative Model · Graph Learning

Author Information

Wamiq Para (King Abdullah University of Science and Technology)
Shariq Bhat (KAUST)
Paul Guerrero (Adobe Research)
Tom Kelly (University of Leeds)
Niloy Mitra (University College London)
Leonidas Guibas (stanford.edu)
Peter Wonka (KAUST)

More from the Same Authors