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

Jiin Choi1,2, Seung Won Lee1,2, Kyung Hoon Hyun1,2
1 Hanyang University , 2Human-Centered AI Design Institute
Paper arXiv Video Code
GenPara demo

GenPara Overview of GenPara, an interactive 3D design editing system that leverages text-conditional shape parameters of 3D design and infers the users’ regions of interest.

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 proposeGenPara, 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 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.

Video

Challenges and Research Goals

Design goals overview
Design goals overview

Key Tools

Design goals overview
  • Text-conditional part-level editing for precise shape modifications using shape parameters.
  • Visualization of the design space to help users navigate design variations effectively.
  • Hierarchical visualization of designs to track and refine design evolution systematically.

LLM Based 3D Generation And Editing

Design goals overview
Design goals overview
Design goals overview

BibTeX

@inproceedings{choi2025genpara,
  title={GenPara: Enhancing the 3D Design Editing Process by Inferring Users' Regions of Interest with Text-Conditional Shape Parameters},
  author={Choi, Jiin and Lee, Seung Won and Hyun, Kyung Hoon},
  booktitle={Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems},
  pages={1--21},
  year={2025}
}