AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala ngu-Immanuel Koh

Uyilo olubizwa ngokuba yi-AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala olwenziwe ngu-Immanuel Koh ngumwini obekekileyo webhaso elinobukhazikhazi le-2025 Ibhaso Lentsimbi le-A' Design Award Kudidi Lokhuphiswano lwe-Uyilo oluVelisayo, olwe-Algorithimu, olweParametrikhi kunye noluNcediswa yi-AI.

IntsimbiOluvelisayo· 2025

AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala

ngu Immanuel Koh

Umxhasi: Immanuel Koh

Umwini we-Ibhaso Lentsimbi le-A' Design Award Kudidi Lwe-Oluvelisayo

60,960

Umwini Webhaso Oqinisekisiweyo

Qinisekisa Isimo Sebhaso se-#170593

Tyelela iSayithi Jonga kwi-A' Design Award Uxwebhu Lweendaba Ibheji Yembasa

Imibala

Uyilo

Malunga ne-AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala

I-Singapore yidolophu eyenziweyo. Iqeqeshwe ngeseti enkulu yedatha yeemodeli zedijithali ezintathu kwizityhalo (3D) zezakhiwo eziphakamileyo ezifumaneka eSingapore, imodeli ye-AI eyilwe ngokukodwa ayivelisi kuphela iindlela ezikholisayo ngokwesimo nezithetha ndawonye ngokwentsingiselo, kodwa iqalisa nokucinga ngeendlela zoyilo ezintsha nezimangalisayo, ngokudibanisa nokwandisa phakathi kweendidi eziqhelekileyo zezindlu eziphakamileyo zokuhlala ezinjengeebhloko ezizicwecwe (slab), ezizincam (point), kunye nezizihlokombe (cluster).

Ukuqatshelwa

Malunga ne-Ibhaso Lentsimbi le-A' Design Award

AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala ngumphumeleli weIbhaso Lentsimbi le-A' Design Award, ukuqatshelwa okuhlonitshwayo okunikwa imiyilo elungileyo eyanelisa iimfuno zobungcali neemveliso ezilindelekileyo kwimveliso ezicwangciswe kakuhle. Abaphumeleleyo beNtsimbi babonisa ubuchule obukhulu, ubuchule obuphezulu, ukuqonda kwengcali namandla okuyila abayili babo. AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala iyathenjwa ukuba ibe yimveliso exatyiswa kakhulu, edunyiswayo nethandwayo esebenzayo neyinto entsha. Lo myilo uphumeleleyo weIbhaso Lentsimbi le-A' Design Award udibanisa iindlela ezilungileyo kakhulu zemboleko kwaye unezimpawu zobuchwephesha ezifanelekileyo ezidityaniswe nolwazi netalente. AI Sampling Singapore Umsebenzi Ophambili: Uyilo Lwezindlu Zokuhlala iyahlonelwa ngenxa yenkcukacha yayo kwaye yacwangciselwa ukunika uphuculo lomgangatho wobomi olunceda ukwenza ihlabathi libe yindawo engcono.

Emva Koyilo

Ikhithi Yeendaba

Iziqinisekiso, amalungu eqela kunye neenkcukacha zobugcisa ezinikezelwe ngumyili.

Iimpawu Ezizodwa: 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.
Imilinganiselo nePakishini: 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.
Iithegi: AI
Ubuchwepheshe Bokuvelisa: 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.
Umngeni Woyilo: 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.
Uphando: 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.
Inkuthazo: 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.
Ubude Beprojekthi: 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.
Ukuhamba Komsebenzi: This is a digital AI x Architecture generative research project, while the dataset was digitally collected from existing physical buildings in Singapore.
Iipathenti: Currently no patent.
Amalungu Eqela: Artificial-Architecture
Amagunya Emifanekiso: All credits: Artificial-Architecture