Façade Design Support System with Control of Image Generation using GAN

Abstract

Designing the façade, which is the front side of a building, is a crucial yet time consuming part of the architectural design process. Advancements in image generation have led to generative models capable of producing creative, high-quality images. However, it is difficult to apply existing image generative models to façade design as the generated images should provide the architect with inspiration while also reflecting the designer's knowledge and building requirements. The existing models are inadequate for controlling image generation. Thus, we propose a system that supports designers in coming up with ideas for façade design by enabling them to intervene in image generation. The proposed system first determines the base image by using text-to-image retrieval. Next, the system generates diverse images using adversarial generation networks and the user selects images in alternation. This allows for repeated divergence and convergence of ideas and provides the user with inspiration. Our experiments demonstrated that the proposed system is able to arrive at the target idea while providing a variety of ideas through controlled generation.

Development of a Method for Commercial Style Transfer of Historical Architectural Facades Based on Stable Diffusion Models

“…Hence, GANs can, to a certain extent, enhance the efficiency of facade design during the initial phases of design projects. Employing GAN models can reduce the cultural knowledge requirements for designers, generating a diversity of images with characteristics of traditional architectural facades, thereby facilitating work in the early stages [16].…”

Knowledge-Driven and Diffusion Model-Based Methods for Generating Historical Building Facades: A Case Study of Traditional Minnan Residences in China

“…A system is also proposed to aid architects by allowing intervention in the image generation process for facade design. It uses text-to-image retrieval to choose a base image, then employs adversarial generation networks to create diverse images from which users can select, fostering idea convergence and divergence [19]. Additionally, GANs can also play a role in urban redevelopment design.…”