Technology Inheritance Fitaovana Famoronana Endrika Rafitra nataon'i Junming Chen

Ny endrika Technology Inheritance Fitaovana Famoronana Endrika Rafitra nataon'i Junming Chen dia mpandresy sarobidy amin'ny 2023 A' Design Award Vy amin'ny Sokajin'ny Fifanintsanana Famolavolana Generativa, Algoritmika, Parametrika ary Ampian'ny AI.

VyGenerativa· 2023

Technology Inheritance Fitaovana Famoronana Endrika Rafitra

nataon'i Junming Chen

Mpanjifa: Chen junming

Mpandresy A' Design Award Vy amin'ny Sokajy Generativa

45,702

Mpandresy Loka Voamarina

Hanamarina ny Sata Loka ho an'ny #150834

Jereo ao amin'ny A' Design Award Fanambarana ho an'ny Mpanao Gazety Marika Loka

Loko

Ny Endrika

Momba ny Technology Inheritance Fitaovana Famoronana Endrika Rafitra

Ny Lova Teknolojia dia fitaovana faharoa artifisialy izay mamorona endrika ivelan'ny trano. Io fitaovana io dia mamorona endrika trano amin'ny fomba rafitra samihafa avy amin'ny soratra ampidirin'ny mpampiasa. Sary tsirairay dia vokarina ao anatin'ny segondra vitsivitsy monja, ary ny endrika dia azo ovana amin'ny fanovana ny famaritana an-tsoratra. Ny rafitra dia naorina tamin'ny alalan'ny fanangonana sy fanamarihana sary an'arivony momba ny rafitra, avy eo dia nohatsaraina ny modely famoronana sary efa misy tamin'ny alalan'ny angon-drakitra vaovao. Ny tanjona dia ny fanampiana ireo mpianatra vaovao mba hahatratrarana haavo ambony amin'ny asa matihanina.

Ny Fankasitrahana

Momba ny A' Design Award Vy

Nandresy ny A' Design Award Vy ny famolavolana Technology Inheritance Fitaovana Famoronana Endrika Rafitra, fankasitrahana malaza omena ny famolavolana tsara izay mahafeno ny fepetra ara-barotra sy ara-indostria andrasana amin'ny famoronana natao tsara. Ny mpandresy Vy dia mampiseho fahaiza-manao lehibe, fahaizana manokana ambony, fahatakarana manam-pahaizana ary fahaizana mamorona an'ireo mpamorona azy. Andrasana ho famoronana ankasitrahana be, ankafizina ary tiana izay azo ampiharina sady vaovao ny famolavolana Technology Inheritance Fitaovana Famoronana Endrika Rafitra. Ity famolavolana nandresy ny A' Design Award Vy ity dia mampiray ny fomba fanao tsara indrindra amin'ny indostria ary manana toetra ara-teknika mahomby mifandray amin'ny fahalalana sy ny talenta. Ny famolavolana Technology Inheritance Fitaovana Famoronana Endrika Rafitra dia hajaina noho ny fitandremany ary natao hanome fanatsarana ny kalitaon'ny fiainana izay manampy hahatonga ny tontolo ho toerana tsara kokoa.

Ao Ambadiky ny Endrika

Fitaovana ho an'ny Mpanao Gazety

Fankasitrahana, mpikambana ao amin'ny ekipa ary antsipiriany teknika nomen'ny mpanao endrika.

Toetra Manokana: 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.
Refy & Fonosana: Generating building exteriors using a fine-tuned stable diffusion technique.
Marika: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
Teknolojia Famokarana: 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.
Fanamby Endrika: 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.
Fikarohana: 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.
Aingam-panahy: 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.
Faharetan'ny Tetikasa: The project has already been completed in 2023.
Fizotr'asa: 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.