PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 3, 2026IEEE Transactions on Visualization and Computer Graphics0 citations

Generative Surface: GenAI-Assisted Semantic Scaffolding for 3D Conceptual Design in Mixed Reality

View Full Paper
YCYu ChaiQZQianyuan ZouZLZihang Liu

Key Points

  • The aim is to enhance the transition from conceptual sketches to 3D models in engineering design using AI.
  • Introduced Generative Surface to assist in 3D sketching.
  • Utilized AI to translate natural language descriptions into interactive 3D surfaces.
  • Evaluated the system against primitive scaffolding and freehand sketching.
  • Enhanced 3D sketching capabilities for designers in immersive environments.
  • Reduced challenges associated with initiation and expression in design.
  • Showed improved alignment between designers' intent and 3D expressions.

Abstract

The transition from conceptual sketch to 3D model poses a major challenge in engineering design. While Mixed Reality (MR) enables direct 3D creation, designers face two key challenges: the Initiation Challenge (lack of meaningful starting points) and the Expression Challenge (difficulty in precise mid-air sketching). We introduce Generative Surface, leveraging AI to translate natural language descriptions into interactive 3D surfaces that aid designers in 3D sketching, simultaneously addressing both challenges. Our system transforms the design workflow into a fluid "describe, generate, sketch, iterate" cycle. Comparative evaluation against primitive scaffolding and freehand mid-air sketching demonstrates that our approach effectively bridges the gap between designers' conceptual intent and 3D sketch expression in immersive environments.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Chai et al. (2026) studied this question.

synapsesocial.com/papers/69cf5dc55a333a821460bbcehttps://doi.org/10.1109/tvcg.2026.3679098
Ask AI
Helpful
Bookmark
Share
View Full Paper