Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé láti ọwọ́ Junming Chen

Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé láti ọwọ́ Junming Chen jẹ́ aṣẹ́gun olókìkí púpọ̀ ti 2023 Àmì-ẹ̀yẹ Irin A' Design Award nínú Ẹ̀ka Ìdíje Àpẹẹrẹ Ìpilẹ̀ṣẹ̀, Àlgọ́rídímù, Párámétrìkì àti Àtìlẹ́yìn-AI.

IrinÌpilẹ̀ṣẹ̀· 2023

Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé

látọ̀wọ́ Junming Chen

Oníbàárà: Junming Chen

Aṣẹ́gun Àmì-ẹ̀yẹ Irin A' Design Award nínú Ẹ̀ka Ìpilẹ̀ṣẹ̀

47,588

Aṣẹ́gun Àmì Ẹ̀yẹ Tí a Jẹ́rìísí

Jẹ́rìísí Ipò Àmì Ẹ̀yẹ fún #150690

Wo ní A' Design Award Ìwé Ìròyìn Àmì Ẹ̀yẹ

Àwọ̀

Àpẹrẹ Náà

Nípa Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé

Ọ̀rọ̀ Ìwé: Generate Images from Lines jẹ́ ẹ̀rọ ìmọ̀ ẹ̀rọ olóye (artificial intelligence) tí ó ń dá àwòrán ìṣàpẹẹrẹ abẹ́nú ilé jáde láti inú àwòrán ìlà. Ẹ̀rọ yìí dá lórí àpẹẹrẹ diffusion tí a ti mú dára sí i, tí a fi ẹ̀kọ́ kọ́ pẹ̀lú àwọn àwòrán abẹ́nú ilé tó ju 20,000 lọ, tí àwọn onímọ̀ ọ̀nà oníṣẹ́ ọwọ́ kójọ tí wọ́n sì ṣàkíyèsí wọn. Àwọn onímọ̀ ọ̀nà a máa fi àpẹẹrẹ ìlà tí wọ́n fi ọwọ́ yà tàbí tí wọ́n ṣe ní ọ̀nà dígítà bọ sínú ẹ̀rọ náà, wọ́n á sì yan ọ̀nà ọ̀ṣọ́ tí wọ́n fẹ́, bí i ti òde-òní, ti Japan, ti Europe tàbí ti China. Àwòrán ìṣàpẹẹrẹ a sì jáde láàárín ìṣẹ́jú àáyá díẹ̀. Àwọn ìyípadà sí ìlànà náà ni a ṣe nípa ṣíṣàtúnṣe àpẹẹrẹ ìlà náà fúnra rẹ̀, nítorí náà kò sí ìwúlò fún ṣíṣe àwòṣe pẹ̀lú ọwọ́ tàbí àtúnṣe àwòrán léraléra.

Ìdánimọ̀ Náà

Nípa Àmì-ẹ̀yẹ Irin A' Design Award

Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé jẹ́ olùborí Àmì-ẹ̀yẹ Irin A' Design Award, ìdánimọ̀ olókìkí tí a fún àwọn àwòṣe tó dára tí wọ́n pàdé àwọn ohun tí iṣẹ́ àti ilé-iṣẹ́ nílò tí a retí láti ọ̀dọ̀ àwọn ẹ̀dá tí a ṣàwòṣe dáradára. Àwọn olùborí Irin ń fi ìjáfáfá ńlá, ìmọ̀ pàtó gíga, òye ògbóǹtarìgì àti agbára ìṣẹ̀dá àwọn olùṣẹ̀dá wọn hàn. A retí pé Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé yóò jẹ́ ẹ̀dá tí a kà sí gidigidi, tí a gbóríyìn fún tí a sì nífẹ̀ẹ́, tó wúlò tó sì ní ìmúṣẹ̀dá tuntun. Àwòṣe tó borí Àmì-ẹ̀yẹ Irin A' Design Award yìí ń kó àwọn ọ̀nà tó dára jùlọ ilé-iṣẹ́ jọ, ó sì ní àwọn ànímọ́ ìmọ̀-ẹ̀rọ tó péye tí a so mọ́ ìmọ̀ ṣíṣe àti ẹ̀bùn. A bọ̀wọ̀ fún Generate Images from Lines Iṣẹ́ Pàtàkì: Ẹ̀rọ Amúgbèrò Ìṣàpẹẹrẹ Abẹ́nú Ilé nítorí ìfọ̀kànbalẹ̀ rẹ̀, a sì ṣàwòṣe rẹ̀ láti pèsè ìmúdára ìgbésí ayé tó ń ran ayé lọ́wọ́ láti di ibi tó dára jù.

Lẹ́yìn Àpẹrẹ Náà

Àkójọ Ìròyìn

Àwọn ẹ̀tọ́, àwọn ọmọ ẹgbẹ́ àti àlàyé ìmọ̀ ẹ̀rọ tí olùṣàpẹrẹ pèsè.

Àwọn Ohun Àkànṣe: The design was done by artificial intelligence (AI) in collaboration with designers. We trained an AI that professionally generates interior designs, which can generate interior designs with different decorative styles based on input line drafts. It solves the problem that the traditional design modification requires remodeling and rendering. It only takes a few seconds to generate a design using this method, and the efficiency of generation and modification is increased by dozens of times.
Ìwọ̀n àti Àpò: Use artificial intelligence to cooperate with designers to generate designs with different decorative styles. The design area is 160 square meters, and the decoration styles include modern, Japanese, European, and Chinese styles.
Àwọn Àkọlé: Artificial intelligence, Human-machine collaboration, Interior design, Generative design, Efficient design, Rapid modification, Controllable design, Decoration style control
Ìmọ̀-ẹ̀rọ Ìṣelọ́pọ̀: The AI technology we use is our improved diffusion model technology. The typical defect of the diffusion model is that it cannot generate design according to specific "decorative style" and "space attribute," which is fatal for interior design. To this end, we re-collected and manufactured a data set containing more than 20,000 interior design renderings and data annotations and handed the data set to AI learning to generate an AI suitable for interior design. The AI can generate interior renderings specifying "decorative style" and "space attributes" by inputting line sketches.
Ìpèníjà Àpèsè: The challenge of this design is to build a professional interior design AI that generates designs of high quality and correct decor. To this end, we asked professional designers to collect and label tens of thousands of interior design images and then handed over the filtered data to AI for training. Make AI understand what is "decorative style," "spatial attributes," and "aesthetic attributes" and generate an interior design with a specified decorative style.
Ìwádìí: Research Background: The interior design process could be more convenient, and the efficiency of design and modification could be higher.
Methods: We trained an AI for professional interior design and used AI to cooperate with people to generate interior designs of various decorative styles from line drawings.
Results: Using our AI, designers can obtain an interior design rendering every few seconds, efficiently generating and modifying designs.
Insights: Our method can quickly generate large batches of interior designs with specified decoration styles and spatial attributes, and the generated results can be changed by modifying the line draft. Design efficiency is improved by eliminating the need for manual modeling and rendering.
Ìmísí: The traditional process of obtaining renderings for interior design is tedious and time-consuming. We use artificial intelligence (AI) to generate interior design, improve design efficiency, and explore new ways of human-computer collaborative design. Specifically, we trained an AI to create interior designs, which can quickly generate and modify designs in cooperation with humans. Changing the design does not require modifying the model and re-rendering, which improves design efficiency.
Àkókò Iṣẹ́ Àkànṣe: The project is located in Guangzhou, Guangdong Province, China, and was designed in 2023.
Ìlànà Ìṣiṣẹ́: 1. Professional designers collect interior design images and mark and screen them.
2. Use the filtered data to train a professional interior design AI.
3. Designers use AI to design.
4. The designer inputs the hand-drawn or design line draft into AI to specify the decoration style.
5. AI generates the interior design of the specified decoration style.
6. The designer adjusts the line draft of the unsatisfactory part of the design and then regenerates the design.
7. After adjusting the line draft and generating it multiple times, a good design is obtained.