_ urban encounter
tag: [work] [phygital] [digi]
classification: Nanshan Digital Public Art Program
location: Overseas Chinese Town Shenzhen China
collaborator: Haotian Zhang & Tianying Li
Shenzhen is a place where multiple cultures encounter one another, where local and international voices converge. This cultural overlap has produced a rich architectural landscape, allowing heterogeneous urban forms to coexist side by side. In our research, we seek moments of encounter among these architectural elements, extracting fragments from different architectural cultures and using them as foundational materials to construct a house for the site-specific “Shenzhen” typographic installation.
Technically, we employ artificial intelligence tools to study and associate architectural fragments from Shenzhen, generating new three-dimensional models. These models are informed not only by visual data, but also by textual descriptions written by our team, derived from collected objects observed in Shenzhen’s urban street views. Through this process, we discovered that generating a 3D object often requires multiple iterations of textual description before the model begins to approximate the physical original. This iterative gap reveals the bias embedded in human visual description and its translation into language, as compared to how AI processes semantic information. We further observed that describing the same object in Chinese can produce results distinct from its direct English translation in text-to-3D operations, exposing how linguistic structure influences spatial interpretation. Simulation software is then used to compute the assembly process, presented through a ninety-second animation that visualizes the growth of the house.
