Scientific Reports
Part-level 3D shape generation driven by user intention inference with preferential Bayesian optimization
Authors: Seung Won Lee, Jiin Choi & Kyung Hoon Hyun
Published: February 07, 2026
Abstract: Advancements in generative artificial intelligence have introduced state-of-the-art models capable of producing impressive visual shape outputs. However, when it comes to supporting decisions during the three-dimensional shape creation process, prioritizing outputs that align with designers' needs over mere visual craftsmanship becomes crucial. Furthermore, designers often intricately combine three-dimensional parts of various shapes to create novel designs. The ability to generate designs that align with the designers' intentions at the part-level is pivotal for assisting designers. Hence, we introduced BOgen, a novel system that empowers designers to proactively generate and synthesize part-level three-dimensional shapes and enhances their overall user experience by reflecting designer intentions through Bayesian optimization. We assessed BOgen's performance using a study involving 30 designers. The results revealed that, compared to the baseline, BOgen fulfilled the designer requirements for three-dimensional shape part recommendations and shape exploration space guidance. Bogen assists designers in navigation and development, offering design suggestions and fostering proactive design exploration and creation during early-stage design ideation.
Executive Impact: Key Performance Uplifts
BOgen, a novel human-AI system, demonstrates significant improvements in design generation efficiency and user satisfaction compared to traditional UI-only methods.
70.5%
Reduction in Mean Uncertainty of Design Intent Inference
113.9%
Increase in Mean Probability of Preferred Chair Identification
20.8%
Increase in Explored Design Area
27.1%
Increase in Number of Explored Design Clusters
30+
Designers Validated BOgen's Efficacy
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
BOgen: Enterprise Process Flow for 3D Design Generation
User Input & Initial 3D Generation
→
User Preference Collection (Selection/Feedback)
→
VAE Latent Space Reduction (2D Exploration Map)
→
Preferential Bayesian Optimization (PBO)
→
AI-Driven Part-Level Synthesis & Refinement
→
Iterative Design Exploration & Output
BOgen integrates VAE and PBO into generative AI frameworks (SALAD & SPAGHETTI) to empower designers with proactive part-level 3D shape generation, reflecting nuanced user intentions. This iterative process guides users through a vast design space efficiently.
| Feature | BOgen (Proposed System) | UIonly (Baseline) |
|---|---|---|
| Design Space Navigation |
|
|
| User Intention Alignment |
|
|
| Discovery of Novel Designs |
|
|
Designer Insights: Real-World Impact of BOgen
Feedback from the 30 participating designers highlights BOgen's ability to transform the early-stage design ideation process. Here are some key testimonials:
Designer P1: "With the system (BOgen), the map offered unexpected design inspirations and shapes. I could view something unique on the map and then scroll to see various variations with (PBO) suggestions, which was helpful."
Designer P7: "There were usable designs in the (PBO) recommendations. The map, with its color information, helped me look at both areas of interest and those that I had not previously considered, aiding in synthesizing elements and invoking images. In the system (UIonly), I could only see a limited range of chairs that appeared in the search, so I wasn't sure about the designs available. However, in the other system (BOgen), through the map and its colors, I could check areas of interest and even areas that I did not care about, allowing me to see the overall designs."
Designer P24: "I had a design intent, and the map distribution was helpful when specifying it. I was looking for a unique shape, and it was great not having to search but to have a guide. A similar recommendation function (PBO) is also helpful for seeking details. The ideation process benefited from observing several similar details."
Summary: Designers consistently reported that BOgen enhanced their ability to navigate vast design spaces, discover novel design elements, and refine their ideas with greater precision and speed. The system's ability to infer and adapt to user preferences, along with its visual exploration map, fostered a more proactive and effective design process.
Calculate Your Potential AI ROI
Estimate the efficiency gains and cost savings your enterprise could realize by implementing similar AI-driven design generation technologies.
Annual Cost Savings
Annual Hours Reclaimed
Your AI Implementation Roadmap
A phased approach to integrate advanced generative AI into your design and development workflows, maximizing adoption and impact.
Phase 01: Strategy & Discovery
Identify key design challenges, assess existing workflows, and define specific objectives for AI integration. This includes data readiness assessment and initial proof-of-concept planning.
Phase 02: Pilot & Customization
Deploy BOgen-like AI capabilities for a specific design team or product line. Customization of models to your proprietary design data and existing toolchains ensures seamless integration and high relevance.
Phase 03: Scaled Deployment & Training
Roll out the AI system across relevant departments. Comprehensive training for designers and engineers ensures full utilization and empowers your team to leverage AI for creative and efficient design exploration.
Phase 04: Continuous Optimization
Establish feedback loops for ongoing model refinement and performance monitoring. Integrate new design data and user preferences to continuously improve the AI's ability to generate relevant and innovative designs.
Ready to Transform Your Design Process?
The future of part-level 3D design is here. Discover how AI can amplify your team's creativity, accelerate ideation, and deliver unparalleled design precision. Let's build your competitive edge.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat