Junming Chen Is Honored with the A' Design Award for Technology Inheritance Generative Architecture in Generative, Algorithmic, Parametric and AI-Assisted Design

Junming Chen acknowledged for generative, algorithmic, parametric and ai-assisted design by the international grand jury of the 2022 - 2023 A' Design Award & Competition

FOR IMMEDIATE RELEASE

COMO, Italy, April 20, 2023 /DesignNewswire/ A' Design Award & Competition has confirmed the A' Design Award in the Generative, Algorithmic, Parametric and AI-Assisted Design category for Technology Inheritance Generative Architecture by Junming Chen, designed for Chen junming. The award was conferred within the 2022 - 2023 A' Design Award & Competition and was reached through blind peer review by an international grand jury panel of established academics, design professionals and press members, who evaluated anonymized entries against predetermined criteria.

What the A' Design Award Means

The Iron A' Design Award is awarded to good designs that meet the rigorous professional and industrial standards set by the A' Design Awards. This recognition is reserved for works that demonstrate a solid understanding of design principles and show creativity within their execution. Recipients of the Iron A' Design Award are acknowledged for their practical innovations and contributions to their respective fields, providing solutions that improve quality of life and foster positive change. These designs are a testament to the skill and dedication of their creators, showcasing their ability to address real-world challenges through thoughtful design.

Regarding Technology Inheritance Generative Architecture

Technology Inheritance is an artificial intelligence tool that generates building exterior designs. The tool creates building appearances in different architectural styles from text entered by the user. Each image is produced in a few seconds, and the design can be changed by editing the text description. The system was built by collecting and labeling thousands of architectural renderings, then fine-tuning an existing image generation model with the new data set. The aim is to help beginners reach a professional level of quality.

About Junming Chen

Junming Chen is a designer and programmer with a multidisciplinary background. He holds a BA in Architecture, an MS in Design, and an MS in Computing. Currently studying for a doctorate in digital media at Macau University of Science and Technology, and working in the Digital Construction Laboratory of Macau University of Science and Technology. Good at using parametric and artificial intelligence technology for design practice. He designed and built several parametric projects. He has also won many design awards and computer awards.

Award Record

Junming Chen is a winner of 3 A' Design Awards, including this recognition. The awards were granted in the 2022 - 2023 edition of the A' Design Award & Competition.

About the A' Generative, Algorithmic, Parametric and AI-Assisted Design Award

The A' Generative Design Award is an international design competition recognizing good generative designs from leading creators and designers worldwide. It is organized within the A' Design Award & Competition and is open to generative designers, algorithmic design professionals, ai-assisted design experts and parametric designers from all countries. Typical entries include algorithmic artworks, parametric architectures, generative graphics, ai-assisted illustrations, computational sculptures and procedural patterns. The awarded generative designs are published at https://dezigners.org/design-category/generative

About A' Design Award & Competition

Organized annually since 2008, A' Design Award & Competition is an international, juried design accolade. The competition is open to entries from all countries. The philanthropic mission of the A' Design Award is to advance society through good design, by recognizing and promoting superior products, projects and services that benefit society, and by creating a global awareness and appreciation for good design practices and principles. Nominations are peer reviewed and evaluated anonymously by an international grand jury panel of established academics, design professionals and press members against predetermined criteria such as functionality, ergonomics, engineering, presentation, innovation, usability, sustainability and technology, with score normalization applied to remove biases. Awards are conferred at Platinum, Gold, Silver, Bronze and Iron levels. Eligible laureates receive the A' Design Prize, which includes the award trophy, the certificate of design excellence, the hardcover yearbook, a lifetime license to use the A' Design Award winner logo, exhibition of awarded works, an invitation to the gala night and award ceremony in Italy, inclusion in the World Design Rankings and Designer Rankings, and public relations and publicity services. Registration, uploading a work and receiving a preliminary score are free of charge, and Professional and Digital Edition laureates are not contractually obliged to pay further fees to claim the A' Design Prize. More information is available at https://competition.adesignaward.com

Press Resources

Winner Page: https://dezigners.org/150834
A' Design Award Page: https://competition.adesignaward.com/150834
Media Showcase: https://www.designnewsroom.com/!150834
Laureate Profile: https://dezigners.org/d/344009

Media Contact

Giulia Ferrari, Press Office
Designers.Org
Via Leone Leoni 32, 22100 Como, Italy
press@designers.org
+39 031 4491953

###

Fact Sheet

The Work

Project: Technology Inheritance Generative Architecture
Function: Generative Architecture
Category: Generative, Algorithmic, Parametric and AI-Assisted Design
Discipline: Design Strategy
Industry: Innovation and Design Industry
Colors: Saddle Brown, Black, Dark Slate Gray, Lavender and Olive
Images: 5
Client: Chen junming

The Recognition

Laureate: Junming Chen
Country: China
Recognition: A' Design Award
Edition: 2022 - 2023
Design ID: #150834

Design Details

Unique Properties: This project trains an AI that professionally generates the appearance of buildings. The AI can generate buildings of different architectural styles according to the text entered by the user. The AI only takes a few seconds to generate the building's appearance, and users can recreate the design by changing the text description. That is, designers can obtain design concept proposals through AI cooperation and continuously optimize the design.
Inspiration: Most people measure the quality of a building by evaluating how it looks. Good architectural exterior design can bring attention and economic benefits. However, the exterior architectural design is complex, and the quality of architectural exteriors designed by excellent designers and beginners varies greatly. This design makes an artificial intelligence (AI) that can expertly generate building exteriors to help beginners achieve designs that approach the quality of master builders.
Research: Research Background: It is difficult for beginners to design high-quality architectural appearances. Methods: This project trained an AI to professionally generate building exteriors, which can contract with designers to complete architectural exterior designs. Results: Using the AI trained in this project, the designer can generate an architectural appearance rendering in just a few seconds. Insights: Using this method, the architectural appearance of a specified style can be generated and modified through text description, and the quality of the generated design is close to that of a professional designer.
Challenge: The challenge of this design is to build a professional architectural design AI for generating high-quality and stylized designs. This project collected and marked thousands of architectural appearance renderings of dozens of well-known architects, created a data set of architectural appearance, and then handed the data set to AI for fine-tuning learning. This project builds an AI to generate a given building's exterior style.
Realization and Technology: The effect of using stable diffusion to produce architectural appearance could be better. The reason is that this mode needs to sufficiently understand the design skills of different designers, resulting in a messy appearance design and low quality. For this, fine-tuning the existing AI is essential. So this project reworked the data set, fine-tuned the critical stable diffusion, and made an AI to generate the specified architectural style to assist the junior designer in the design.
Operation and Interaction: 1. Professional designers collect and mark, and screen images of outstanding designer building exteriors. 2. Use the filtered data to train an AI that specializes in generating the exterior of a given architectural style. 3. Designers use AI to design. 4. The designer inputs the design text description into the AI to specify the decoration style. 5. AI generates the interior design of the specified decoration style. 6. Modify the unsatisfactory details in the design through text description, and regenerate the design. 7. After adjusting the text description and generating it multiple times, a good design is obtained.
Project Duration and Location: The project has already been completed in 2023.
Specifications: Generating building exteriors using a fine-tuned stable diffusion technique.
Keywords: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control