Skip to main content Skip to secondary navigation

Bridging Design and Fabrication via Neuro-Symbolic Visual Program Synthesis and Rendering

Main content start
Banner Bridging Design
Banner Bridging Design

Research Team

Our Motivation:

“Our research will bring together recent advances in artificial intelligence (AI), computer vision, graphics, and fabrication, leading to both fundamental innovations in neuro-symbolic AI and neural/inverse rendering, and significant industrial impacts in applications that facilitate designers, builders, and owners..”


Icon Contribution

Research Contribution

Seamless integration of multiple data modalities for bridge owners, designers, and builders.

Use of inverse and neural rendering to connect 3D shapes/scene layouts and 2D images.

Develop neuro-symbolic program synthesis and execution algorithms to infer vectorized CAD models for fabrication from raw shapes.

Icon Problem


Practical Problem

Owners, designers, and builders are three key players in the design and fabrication processes; however, the type of data that each group works with is fundamentally different, due to various engineering and cognitive constraints.
Owners may suggest to designers the preferred layout, furniture shape, texture, or fabric via 2D raw images, sketches, and line drawings, designers mostly work with 3D data, such as meshes and primitives, and builders would need detailed fabrication instructions, such as CAD and BIM models.

Conceptual Problem

The collaboration and communication cost among owners, designers, and builders remains high and can be alleviated with new algorithms and tools.

Icon Solution


Bridge design and fabrication by inferring such sequence information from raw data via neuro-symbolic visual program synthesis and rendering.

Icon added value

Added Value For The Industry

Our research will directly benefit owners, designers, and builders, by significantly reducing their collaboration and communication cost and workload, and improving the flexibility and richness in design and fabrication. Ultimately, we hope our research will lead to the fundamental integration of the three parties.

Icon Cooperation partner

Cooperation Partner

Logo for autodesk


Chin-Yi Chang

Research Manager and Principal Research Scientist at Autodesk AI Lab

Ran Zhang

Sr. Research Scientist - Machine Learning at Autodesk

Icon Timeline





Year 2021

Research became awarded: Bridging Design and Fabrication via Neuro-Symbolic Visual Program Synthesis and Rendering


Fall 2021

Start working with industry partners on case-studies


Fall 2021

Literature review to understand product metrics


Winter 2021

Problem formulation and pilot data collection


Winter 2021

Building initial prototypes


If you want to participate in the project please reach out to the Research Team.


Seed Research is in progress and will be continued in the academic year 2022/23.

Research Update & Progress Report

Relevant Links for this Research