DeepCloud. The Application of a Data-driven, Generative Model in Design
This work addresses designers by offering a more automated and intuitive generative design tool, though it appears incremental as it builds on existing autoencoder architectures.
The paper tackles the problem of generative design systems requiring explicit designer input by developing DeepCloud, a data-driven generative model that learns from existing solutions to produce design alternatives, resulting in an intuitive web-based interface with analog input devices.
Generative systems have a significant potential to synthesize innovative design alternatives. Still, most of the common systems that have been adopted in design require the designer to explicitly define the specifications of the procedures and in some cases the design space. In contrast, a generative system could potentially learn both aspects through processing a database of existing solutions without the supervision of the designer. To explore this possibility, we review recent advancements of generative models in machine learning and current applications of learning techniques in design. Then, we describe the development of a data-driven generative system titled DeepCloud. It combines an autoencoder architecture for point clouds with a web-based interface and analog input devices to provide an intuitive experience for data-driven generation of design alternatives. We delineate the implementation of two prototypes of DeepCloud, their contributions, and potentials for generative design.