Autonomous driving systems require High-Definition (HD) semantic maps to navigate
around urban roads. Existing solutions approach the semantic mapping problem by offline …

Deep generative models of 3D shapes have received a great deal of research interest. Yet,
almost all of them generate discrete shape representations, such as voxels, point clouds …

We introduce SceneScript, a method that directly produces full scene models as a sequence
of structured language commands using an autoregressive, token-based approach. Our …

CAD modeling, despite being the industry-standard, remains restricted to usage by skilled
practitioners due to two key barriers. First, the user must be able to mentally parse a final …

We view the reconstruction of CAD models in the boundary representation (B-Rep) as the
detection of geometric primitives of different orders, ie, vertices, edges and surface patches …

Conceptual design is the foundational stage of a design process that translates ill-defined
design problems into low-fidelity design concepts and prototypes through design search …

Data-driven intelligent computational design (DICD) is a research hotspot that emerged
under fast-developing artificial intelligence. It emphasizes utilizing deep learning algorithms …

Abstract We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a
set of extrusion cylinders. Reverse engineering from a raw geometry to a CAD model is an …

This work explores a novel image geometric abstraction paradigm based on assembly out of
a pool of pre-defined simple parametric primitives (ie, triangle, rectangle, circle and …

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 …