AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo ka Immanuel Koh

Moralo oa AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo ka Immanuel Koh ke mohlodi oa khau e hlomphehang haholo ya 2025 Moputso oa Tšepe oa A' Design Award Mokhahleong oa Tlhodisano oa Moralo wa Tlhahiso, Algorithimi, Paramethrike le AI.

TšepeTlhahiso· 2025

AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo

ka Immanuel Koh

Moreki: Immanuel Koh

Mohlodi oa Moputso oa Tšepe oa A' Design Award Mokhahleong oa Tlhahiso

60,008

Mohlodi oa Khau ea Netefaditsweng

Netefatsa Boemo ba Khau bakeng sa #170593

Etela Sebaka Sheba ho A' Design Award Tokollo ya Boraditaba Baeche ya Moputso

Mebala

Moralo

Mabapi le AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo

Sengoliloeng sa Buka: Singapore ke motse o entsoeng ke batho. Ka ho koetlisoa ka data e kholo ea mehlala ea dijithale ea 3D ea meaho e melelele e fumanoang Singapore, mohlala oa AI o qapiloeng ka tsela e khethehileng ha o hlahise feela mokgwa o utloahalang sebopehong le o utloahalang ka moelelo, empa o qala hape ho nahana ka mefuta e mecha le e makatsang ea boqapi, e kopanyang le ho atolosa lipakeng tsa mefuta e tloaelehileng ea matlo a bolulo a melelele a kang li-slab, li-point le li-cluster block.

Kamohelo

Mabapi le Moputso oa Tšepe oa A' Design Award

AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo ke mohapi oa Moputso oa Tšepe oa A' Design Award, kananelo e hlomphehang e fuoang meralo e metle e finyellang litlhoko tsa porofeshenale le tsa indasteri tse lebelletsoeng ho lintho tse hlahisitsoeng tse entsoeng hantle. Bahapi ba Tšepe ba bontša bokhoni bo boholo, bokhethehi bo phahameng, kutloisiso ea litsebi le bokhoni ba boqapi ba baqapi ba bona. AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo e lebelletsoe ho ba ntho e hlahisitsoeng e hlomphuoang haholo, e ratoang le e ratehang, e sebetsang le e nang le mehopolo e mecha. Moralo ona o hapileng Moputso oa Tšepe oa A' Design Award o kenyelletsa mekhoa e metle ka ho fetesisa ea indasteri mme o na le litšobotsi tsa theknoloji tse nang le bokhoni tse amanang le tsebo le talenta. Ka lebaka la botlalo ba eona, AI Sampling Singapore Mosebetsi o ka Sehloohong: Boqapi ba Matlo a Bolulo e tšoanelehela tlhompho mme e entsoe ho fana ka ntlafatso ea bophelo e thusang ho etsa hore lefatše le be sebaka se molemo.

Ka Mora Moralo

Sete ya Boraditaba

Litlhaku, ditho tsa sehlopha le lintlha tsa botekgeniki tse fanoeng ke moetsi wa moralo.

Boleng bo Ikhethang: Is it possible to sample at scale and at high-resolution every single building ever built in a country? If so, can such a dataset be used to train an AI model in generating new yet locally compliant buildings without any explicit regulatory control inputs? The project explores the design agency of deep generative neural networks in learning three-dimensional exteriority and interiority with a redesigned 3D generative adversarial network (3D-GAN) AI model. Winner of WAFX2024, IDA2024 and BLT2024.
Boholo le Phuthelo: This is a digital AI x Architecture project. Each generated output is a new high-rise high-density residential public housing of up to 30 floors.
Lithegi: AI
Theknoloji ya Tlhahiso: A custom generative AI model was trained from scratch using proprietary code base and dataset. Specifically, a 3D generative adversarial network (3D-GAN) AI model was trained to learn semantic and spatial configuration of high-rise high-density residential public housing in Singapore.
Phephetso ya Moralo: The non-existence of 3D models and their corresponding floor plans was the first challenge. New workflow and tools had to be developed to not only collect (i.e., digitally and physically), but create (annotate) and curate (i.e., exploratory data analysis) such high quality dataset to train an AI model from scratch. Technically difficult due to the scalability of similar CAD representation which was overcome via a novel AI latent representation of 3D.
Dipatlisiso: A custom generative AI model was trained from scratch using proprietary code base and dataset. Specifically, a 3D generative adversarial network (3D-GAN) AI model was trained to learn semantic and spatial configuration of high-rise high-density residential public housing in Singapore.
Kgothaletso: Singapore is an artificial city! Trained with a large dataset of 3D digital models of high-rise buildings found in Singapore, the custom-designed AI model generates not only formally plausible and semantically coherent configurations, but begins to also imagine novel and uncanny architectural forms, interpolating and extrapolating among standard high-rise housing typologies such as the slab, point, and cluster blocks. Project exhibited at Venice Architecture Biennale and Singapore's Arts House.
Nako ya Projeke: This is an on-going and longer-term AI x Architecture research being conducted at the university design lab since 2021. It was however only published much later as an official architectural design award entry from 2024 onwards.
Tsamaiso ya Mosebetsi: This is a digital AI x Architecture generative research project, while the dataset was digitally collected from existing physical buildings in Singapore.
Diphatente: Currently no patent.
Litho tsa Sehlopha: Artificial-Architecture
Litlotla tsa Setshwantsho: All credits: Artificial-Architecture