GenPara: Enhancing the 3D Design Editing Process by Inferring Users' Regions of Interest with Text-Conditional Shape Parameters

Abstract

In 3D design, specifying design objectives and visualizing complex shapes through text alone proves to be a significant challenge. Although advancements in 3D GenAI have significantly enhanced part assembly and the creation of high-quality 3D designs, many systems still to dynamically generate and edit design elements based on the shape parameters. To bridge this gap, we propose GenPara, an interactive 3D design editing system that leverages text-conditional shape parameters of part-aware 3D designs and visualizes design space within the Exploration Map and Design Versioning Tree. Additionally, among the various shape parameters generated by LLM, the system extracts and provides design outcomes within the user's regions of interest based on Bayesian inference. A user study N = 16 revealed that \textit{GenPara} enhanced the comprehension and management of designers with text-conditional shape parameters, streamlining design exploration and concretization. This improvement boosted efficiency and creativity of the 3D design process.

21 pages, 18 figures

References in corpus (19)

• ShapeNet: An Information-Rich 3D Model Repository
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models
• Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation
• Graphologue: Exploring Large Language Model Responses with Interactive Diagrams
• DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models
• Sequential Gallery for Interactive Visual Design Optimization
• How Can Large Language Models Help Humans in Design and Manufacturing?
• AdaptiFont: Increasing Individuals' Reading Speed with a Generative Font Model and Bayesian Optimization
• ConceptScope: Organizing and Visualizing Knowledge in Documents based on Domain Ontology
• Amortised Experimental Design and Parameter Estimation for User Models of Pointing
• DualSDF: Semantic Shape Manipulation using a Two-Level Representation
• GenQuery: Supporting Expressive Visual Search with Generative Models
• SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation
• CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization
• SketchINR: A First Look into Sketches as Implicit Neural Representations
• Spice-E : Structural Priors in 3D Diffusion using Cross-Entity Attention
• Neural Wavelet-domain Diffusion for 3D Shape Generation
• Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes