This research demonstrates how AI transcends mere visual generation to become a new pathway for the dynamic preservation and revitalization of cultural heritage.
Abstract
As a representative of cultural heritage, Suzhou Ming-style furniture embodies a composite knowledge system integrating material properties, structure, and craftsmanship. While Generative AI shows potential in creative design, current models lack an intrinsic understanding of physical and manufacturing constraints, often producing unproducible visual illusions. To bridge the gap between pixelated images and actual production, this paper proposes and develops a production-aware AI co-creation system that translates implicit traditional craftsmanship into explicit digital rules. Utilizing a node-based workflow and a knowledge-embedded estimation module, the system connects creative exploration with production configuration. It generates multimodal outputs, including renderings, structural exploded views, and practical cost and timeline estimations. Preliminary evaluations indicate high consistency with actual workshop production experience, effectively lowering the creative threshold for non-professionals. This research demonstrates how AI transcends mere visual generation to become a new pathway for the dynamic preservation and revitalization of cultural heritage.
The goal is not to present AI as a replacement for artists, but to show how controllable AI systems can support more precise, collaborative, and extensible forms of creative production.
Zheng Wei, Yuying Tang, Mia Tang et al.· Proceedings of the Special I...· 0 citations
A human-in-the-loop GenAI-assisted framework for producing immersive 3D visualization prototypes rather than historically verified reconstructions is proposed, which integrates multi-view image generation, knowledge-informed review, single-image-to-3D generation, topology inspection, and perceptual calibration.
Traditional virtual scene and character design suffers from low efficiency and cultural misalignment in AI - generated content. In the context of computer vision and virtual reality, this misalignment also raises concerns about digital media information security and authenticity. This paper proposes a work order - driven AIGC framework for virtual anime scene and character generation. A prompt parser is introduced to convert unstructured enterprise work orders into structured workflows, which then guide generative tools for end - to - end generation. To address cultural misalignment, a Lingnan Cultural Gene Library is constructed and parameterized constraints are applied to traditional elements during generation. A human - in - the - loop mechanism is integrated at the 2D - to - 3D transition node to combine AIGC efficiency with manual topological precision. Experiments on a dataset of 150 enterprise work orders for Lingnan virtual scenes and characters show that the proposed framework reduces design iteration time by 42% (from 68.5 h to 39.6 h) and improves cultural element accuracy from 78% to 92% (p < 0.01) compared with traditional 3D modeling pipelines, providing an efficient and culturally aware solution for AIGC applications in virtual reality and multimedia content generation, while also enhancing the security and authenticity of digital cultural media.
Ai-Guo Sun· 2026 3rd World Conference on...· 0 citations
As Extended Reality (XR) evolves into an immersive computing medium, interactive 3D authoring becomes essential for creative and functional workflows. However, existing generative XR systems produce monolithic outputs lacking explicit semantic structure, limiting post-generation control. We introduce PartInteractor, a representation-to-interaction framework that investigates how semantic part hierarchies can be incorporated into generative XR authoring, and exposed as first-class, directly manipulable units, turning one-shot prompt-to-object generation into continuous component-level co-creation. PartInteractor supports speech, sketch, and image inputs, integrating an LLM interpreter with a retrieval-generation strategy to scaffold user intent prior to 3D generation. Instead of producing monolithic objects, our system generates semantically decomposed 3D assets with explicit part hierarchies, enabling rich component-level interaction over object structure and composition. Our evaluations suggest that part-aware representation increases post-generation control and reduces reliance on whole-object regeneration, while intent scaffolding mitigates ambiguity and improves intent-result alignment, together supporting more expressive and controllable human-AI co-creation workflows. These results highlight part-aware representation and intent scaffolding as promising design considerations for future generative XR authoring systems.
The preservation and innovation of intangible cultural heritage present significant challenges, while AI technology offers new opportunities for its protection and inheritance. Nevertheless, when AI technology is applied to the integrated design of intangible cultural heritage and classic animation IPs, issues such as misinterpretation of cultural symbols, distortion of traditional patterns, and separation from the original context, referred to as "de-contextualization" problems, are prone to occur. This makes it arduous to achieve the precise integration of the characteristics of intangible cultural heritage and classic art styles. This paper delves into the application of AIGC in the integration of Wuxi Wedding Embroidery patterns and the domestic animation IP The Golden Conch. By establishing a multimodal dataset, conducting LoRA model training, and leveraging ComfyUI-assisted generation, an AI-assisted design closed-loop workflow is developed. This workflow encompasses "extraction of intangible cultural heritage cultural genes – construction of a multimodal fusion gene library – cross-media translation and encoding of cultural symbols – generation of the AIGC workflow – implementation of design results and value extension". This research can offer practical references for the contemporary activation and digital dissemination of intangible cultural heritage patterns, as well as provide ideas and paradigms for the innovative design of classic domestic animation IPs.
This study proposes an AI-driven generative design workflow that translates semantic inputs into 2D imagery and 3D models, enabling the systematic learning and replication of stylistic features from a quintessential southern Chinese architectural ornament—the Lingnan stucco relief.
Yiwei Yin, Jiale Cheng, Jiashao Zhou et al.· AI in Civil Engineering· 0 citations