Aug 2026· International Conference on Computer Graphics and Virtuality· Vol 14315, pp. 143150E - 143150E-9· 0 citations· 15 references
Engineering
TL;DR
Differences in output forms, final quality, and entry barriers between AIGC modeling and traditional modeling mean that the two 3D design approaches are not in an oppositional relationship, and a human-led, AI-assisted collaborative mode is bound to be an important trend in the future innovative development of 3D digital design.
Abstract
As AIGC (AI-generated content) technology develops at high speed, AIGC participates in design from different dimensions. In 3D design, generative modeling largely relieves the pressure of high-intensity repetitive work; however, the precision of generative models is not comparable to 3D models routinely designed by designers. Based on this situation, this study takes the digital design practice of Minnan patterned tile as an example to compare the similarities and differences between the traditional 3D modeling workflow and the AIGC-assisted modeling workflow. This paper holds that differences in output forms, final quality, and entry barriers between AIGC modeling and traditional modeling mean that the two 3D design approaches are not in an oppositional relationship; we can take the essence of each and combine their advantages to carry out 3D design work, and a human-led, AI-assisted collaborative mode is bound to be an important trend in the future innovative development of 3D digital design.
While generative AI has unlocked new opportunities for 3D content creation, current workflows often rely on multiple regenerations, which provides limited control and unpredictable outcomes. We present Compos3D, a system that introduces a compositional workflow for generative 3D modeling through remixing. Instead of repeatedly regenerating models, users generate multiple candidates from text or image prompts, select parts of interest via 2D image regions or 3D mesh segments, and assemble them into a coherent design. The system synthesizes these compositions into a refined 3D model, preserving high-level intent while resolving low-level geometry. To evaluate this approach, we conducted a controlled user study comparing remixing and regeneration workflows across both 2D and 3D modalities. Results show that the remixing workflow provides participants with greater creative control, stronger alignment with their intent, and higher satisfaction. We conclude with design recommendations for future AI-assisted 3D modeling workflows.
Faraz Faruqi, Sean J. Liu, George Fitzmaurice et al.· 0 citations
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
The digital transformation of the apparel industry is increasingly driven by the integration of 2D pattern development and 3D virtual simulation technologies. This study focuses on the digital 3D garment development process using VStitcher (Browzwear), presenting a structured workflow from the initial design concept to the final virtual prototype. The proposed approach emphasizes the transition from traditional physical sampling to digital prototyping, enabling improved efficiency, faster design interactions, and reduced material consumption. The workflow includes 2D pattern construction, material definition and mapping, virtual garment assembly, 3D simulation, and fit evaluation on a digital avatar. The results demonstrate that integrating 2D and 3D environments creates a continuous feedback loop that supports iterative refinement of design parameters and early detection of construction and fit issues. The study further confirms that virtual prototyping, supported by styling tools, enhances garment evaluation by enabling advanced manipulation and simulation of manual fitting adjustments. This contributes to reduced physical sampling, improved development accuracy, and increased workflow efficiency. However, simulation accuracy remains dependent on precise pattern construction, material parameter definition, garment complexity, and user expertise, while certain tactile fabric properties cannot yet be fully replicated digitally. Overall, the study demonstrates that 3D garment development systems such as VStitcher provide a robust methodological framework for more efficient, accurate, and sustainable apparel product development in both industrial and educational contexts.
Generative AI lets anyone create rich visual content in seconds, yet translating that content into a physically fabricable artifact still demands manual decomposition, occlusion repair, and structural verification that most tools leave entirely to the user. We present FabDreamer, an image-to-physical system that carries an image to fabrication-ready SVGs through three stages with deliberately staged AI initiative: (1) AI leads decomposition into depth-ordered layers, (2) assists on demand during creative editing with realtime 3D preview, and (3) advises on structural integrity before export. We instantiate this workflow for layered laser-cut art and evaluate it through three rounds including a formative analysis, an early prototype user evaluation (N=13), and a cross-domain practitioner study with specialists from 6 fabrication domains (N=6). Our findings show that physical awareness during design opens creative opportunities beyond error prevention, that practitioners appropriate the system's generic geometric operations for their own domains, and that the fabrication agent covers geometry-readable constraints while domain knowledge remains with the maker.
Chenfeng Gao, Zeya Chen, Anjie Yang et al.· 0 citations
Creating 3D assets is essential for game development. Modeling requires time and technical skills, and fast prototyping is challenging, especially for novice designers. To make complex 3D modeling more accessible while strengthening creativity, we present CreatureCreator, a tool that enables users to generate 3D models from an image of a created artifact. We investigated two input modalities: drawing with pen and paper and sculpting with clay. Adding an analog input modality to the generation process could lower the entry barrier for diverse user groups, enabling intuitive and creative modeling. In a within-subject study with game design-experienced participants (n=20), both modalities scored highly for user experience, engagement, and creativity support, with the clay input especially valued for its generated models and enhanced sense of control. The interaction workflow supports playful exploration by allowing users to experiment with parameters and using AI as a production and/or ideation partner.
Lisa Hesselbarth, Nina Wenig, Rachel Ringe et al.· Creativity & Cognition· 0 citations
The foundations of fashion design and pattern making, specifically referring to the process of leaving manual operations and transitioning to the digital workflow assisted by AI. It examines the most significant design approaches, including sketch-based, draping-first, pattern-first, textile-led, and concept-driven, and their contribution to the transformation of ideas into a prototype garment, via the process of fitting and refinement. The importance of Computer-Aided Design (CAD) systems in improving accuracy, efficiency, grading, and virtual prototyping is addressed, combined with such advanced features as 3D body scanning, parametric modeling, and simulation. The paper also investigates the revolutionary nature of Artificial Intelligence in automatic design creation, trend predicting, one-to-one suggestions, and virtual clothing fashioning. Significant AI methods, such as GANs, CNNs, VAEs, reinforcement learning, and NLP, are discussed as having a role to play in the creative design process, visual interpretation, and consumer-driven fashion systems. The traditional pattern-building techniques, flattening and computerized garment solutions are also discussed. Lastly, the paper outlines the main issues, including data quality, high implementation cost, creativity issues, sustainability integration, and lack of standardization, which should be considered as future direction of intelligent fashion design systems.
Jagadishwar Reddy Reddygari· Journal of Management and Ec...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
