Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi na Junming Chen

Umushinga Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi wa Junming Chen ni uwatsinze igihembo cyubahwa cyane 2023 Igihembo cya A' Design Award cy'icyuma mu Cyiciro cy'Ihiganwa cya Igishushanyo Gishingiye ku Ikoranabuhanga.

IcyumaIgishushanyo Gishingiye ku Ikoranabuhanga· 2023

Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi

na Junming Chen

Umukiriya: Chen junming

Uwatsinze Igihembo cya A' Design Award cy'icyuma mu Cyiciro cya Igishushanyo Gishingiye ku Ikoranabuhanga

45,702

Uwatsinze Igihembo Yemejwe

Emeza Uko Igihembo Gihagaze ku #150834

Reba kuri A' Design Award Itangazo ry'Ikinyamakuru Ikimenyetso cy'Igihembo

Amabara

Imigereranyo

Ibyerekeye Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi

Technology Inheritance ni igikoresho gikoresha ubwenge bw'ubukorano gikora ibishushanyo by'imbonerahamwe y'inyubako. Iki gikoresho gikora imiterere y'inyubako mu buryo butandukanye bw'ubwubatsi bushingiye ku magambo umukoresha yanditse. Buri shusho ikorwa mu masegonda make, kandi igishushanyo gishobora guhindurwa hifashishijwe guhindura inyandiko isobanura icyifuzo. Iyi sisitemu yubatswe binyuze mu gukusanya no gushyiraho amazina ku bishushanyo by'ubwubatsi ibihumbi n'ibihumbi, hanyuma hakoreshwa uwo mwanya w'amakuru mushya kugira ngo hanonosorwe moderi isanzweho ikora amashusho. Intego ni ugufasha abatangiye kugera ku rwego rw'ubuhanga rw'abanyamwuga.

Ishimwe

Ibyerekeye Igihembo cya A' Design Award cy'icyuma

Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi ni uwegukanye Igihembo cya A' Design Award cy'icyuma, ishimwe ry'agaciro ritangwa ku bishushanyo byiza bihuza ibyo umwuga n'inganda bikeneye ku bihangano byashushanyijwe neza. Abegukanye icyuma bagaragaza ubuhanga bukomeye, ubumenyi bwihariye, imyumvire y'inzobere n'ubushobozi bwo guhanga bw'ababikoze. Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi biteganyijwe ko izaba igihangano cyubahwa, gishimwa kandi gikundwa, gifatika kandi gifite udushya. Iki gishushanyo cyegukanye icyuma gihuza uburyo bwiza bukoreshwa mu nganda kandi gifite ibiranga bya tekiniki bifite ubushobozi, bifatanye n'ubumenyi n'impano. Technology Inheritance Igikoresho cyo Gukora Igishushanyo cy'Ubwubatsi yubahwa kubera gukora neza, kandi yashushanyijwe kugira ngo inoze ubuzima, ifashe gutuma isi iba nziza.

Inyuma y'Imigereranyo

Dosiye y'Itangazamakuru

Amazina y'abagize uruhare, abagize itsinda n'amakuru y'ubuhanga byatanzwe n'umuhanzi.

Ibintu Bidasanzwe: 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.
Ibipimo n'Ipaki: Generating building exteriors using a fine-tuned stable diffusion technique.
Ibibazo Fatizo: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
Ikoranabuhanga ryo Guteza Imbere: 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.
Ikibazo cy'Ishusho: 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.
Ubushakashatsi: 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.
Ibyatumye Habaho: 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.
Igihe cy'Umushinga: The project has already been completed in 2023.
Uburyo bw'Imikorere: 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.