Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale na Junming Chen

ʻO Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale na Junming Chen he mea lanakila hanohano loa o ka 2023 A' Design Award Hao ma ka Māhele Hoʻokūkū Hoʻolālā Hoʻohua, ʻAlakaiʻo, Hōʻailona a me AI Kōkua.

HaoHoʻohua· 2023

Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale

na Junming Chen

Mea Kūʻai: Chen junming

Mea Lanakila A' Design Award Hao ma ka Māhele Hoʻohua

45,702

Mea Lanakila i Hōʻoia ʻIa

Hōʻoia i ke Kūlana Makana no #150834

Nānā ma A' Design Award Hoʻolaha Nūhou Hōʻailona Makana

Nā Waihoʻoluʻu

Ka Hoʻolālā

E Pili Ana iā Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale

ʻO Technology Inheritance he mea hana naʻauao lima hana i hoʻokumu ai i nā hoʻolālā o waho o nā hale kūkulu. Hoʻokumu kēia mea hana i nā helehelena hale ma nā ʻano kūkulu like ʻole mai ka ʻōlelo i kākau ʻia e ka mea hoʻohana. Hoʻopuka ʻia kēlā me kēia kiʻi i loko o kekahi mau kekona, a hiki ke hoʻololi i ka hoʻolālā ma o ka hoʻoponopono ʻana i ka wehewehe ʻōlelo. Ua kūkulu ʻia ka ʻōnaehana ma o ka hōʻiliʻili ʻana a me ka kāpae inoa ʻana i nā tausani o nā kiʻi hoʻolālā kūkulu hale, a laila hoʻomaikaʻi hou ʻia kekahi kumu hoʻohālike hoʻopuka kiʻi e kū nei me kēia ʻikepili hou. ʻO ka pahuhopu, ʻo ia ka kōkua ʻana i ka poʻe hoʻomaka e hiki ai ke kiʻi aku i kekahi pae kūlana ʻoihana kiʻekiʻe.

Ka Hoʻomaikai

E Pili Ana i ka A' Design Award Hao

Ua lanakila ka hoʻolālā Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale i ka A' Design Award Hao, he ʻike hoʻohanohano i hāʻawi ʻia i nā hoʻolālā maikaʻi e hoʻokō ana i nā koi ʻoihana a ʻoihana hana i manaʻo ʻia mai nā mea hoʻokumu i hana maikaʻi ʻia. Hōʻike nā lanakila Hao i ka mākau nui, ka loea kiʻekiʻe, ka ʻike akamai a me ka hiki hana noʻeau o ka poʻe i hana iā lākou. Manaʻo ʻia ʻo ka hoʻolālā Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale he mea hoʻokumu i mahalo nui ʻia, hoʻohiwahiwa ʻia a aloha ʻia e pono a hou. ʻO kēia hoʻolālā i lanakila i ka A' Design Award Hao e hoʻohui ana i nā hana maikaʻi loa o ka ʻoihana a loaʻa nā ʻano ʻenehana mākaukau i hui pū ʻia me ka ʻike hana a me ka makakoho. Mahalo ʻia ka hoʻolālā Technology Inheritance He Mea Hana no ka Hoʻokumu ʻAno Kūkulu Hale no kona nānā pono a ua hoʻolālā ʻia e hāʻawi i nā hoʻomaikaʻi ola e kōkua ai i ka hana ʻana i ka honua i wahi maikaʻi aku.

Ma Hope o ka Hoʻolālā

ʻEke Nūhou

Nā hōʻoia, nā lālā hui a me nā kikoʻī ʻenehana i hāʻawi ʻia e ka mea hoʻolālā.

Nā ʻAno Kūʻokoʻa: 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.
Nā Ana a me ka Hoʻopili: Generating building exteriors using a fine-tuned stable diffusion technique.
Nā Lepili: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
ʻEnehana Hana: 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.
Pilikia Hoʻolālā: 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.
Noiʻi: 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. This method does not require manual modeling and rendering, which improves design efficiency and quality.
Hoʻoulu Manaʻo: 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.
Ka Lōʻihi o ka Papahana: The project has already been completed in 2023.
Kaʻina Hana: 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.