Posts

ARCH Seminar. Memory of the World

/in /by

Digital Heritage through VR and Generative AI

ARCH 7036-04/ARCH5051-04.Elective Theory Seminar, SAID, DAAP, Spring 2025

Class time: Monday. 10 am -12:50 pm.  Classroom: 4425-E, CGC Lab, DAAP building. 

Faculty: Ming Tang, Professor in Architecture and Interior Design, DAAP. Director of  Extended Reality Lab. XR-Lab

Seminar Description

This seminar invites students to explore the intersection of architecture, history, artificial intelligence, and immersive technologies by reimagining the past through digital heritage. Drawing on historic documents and archival materials from Cincinnati, students will work closely with historians to reconstruct a Cincinnati neighborhood as it existed in the 1950s, allowing users to step back in time and experience its spaces and stories through immersive visualization and virtual reality (VR).

Throughout the semester, students will investigate how generative AI, virtual reality (VR), and interactive visualization can preserve and reinterpret cultural memory. Using Unreal Engine as the primary platform, participants will design interactive VR environments for mobile headsets, creating spaces where history, atmosphere, and narrative merge into immersive experiences. The seminar aligns with UNESCO’s  Memory of the World initiative, emphasizing the preservation of documentary and architectural heritage for future generations.

In addition to a large collaborative group project, each student will conduct a samll individual research-based design investigation focused on a “lost” historic artifact—such as a forgotten art work or street furniture. Through AI-assisted modeling, reality capture, and digital prototyping, students will gain hands-on experience reconstructing the intangible layers of history while developing advanced technical and conceptual skills in digital heritage creation.

Read more

Human Digital Twin

/in /by

High-Fidelity Digital Human Modeling and Visualization

This research investigates advanced methods for constructing high-fidelity digital humans, with a focus on both technical innovation and applied use in immersive environments. The project integrates generative artificial intelligence, image-based modeling, and visualization pipelines to advance realism, interactivity, and usability in human–computer interaction.

Aim 1. Conversational Digital Agents Driven by Large Language Models (LLMs).
The first aim is to utilize large language models (LLMs) as the core engine for conversational digital humans. By embedding LLM-driven reasoning into virtual agents, the project seeks to create responsive, adaptive, and context-aware “talking agents.” These agents will simulate naturalistic dialogue, provide interactive guidance, and adapt to user needs across diverse scenarios such as education, healthcare training, and collaborative design.

Aim 2. Photorealistic Skin and Visual Fidelity Through Scanned Data.
The second aim focuses on the visual accuracy of digital humans. High-resolution image scans will be processed to reconstruct human skin with detailed fidelity, including surface textures, translucency, and micro-geometric variations. The resulting models are capable of 4K photorealistic rendering (click image to view sample output), significantly enhancing realism in simulation and visualization. This fidelity is crucial for applications where nuanced perception—such as empathy, trust, or attentiveness—depends on subtle visual cues.

Significance.
By combining intelligent conversational capabilities with photorealistic appearance, this research advances the next generation of digital humans. The outcomes will support applications in extended reality (XR), therapeutic and clinical training, collaborative design education, and digital twin environments, where authenticity of both interaction and appearance directly influences user engagement and effectiveness

High-fidelity digital human.

Read more