ArXiv TLDR

SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design

🐦 Tweet
2605.07894

Yichen Andy Yu, Wanru Li, Qiaoran Wang, Jymon Ross, Gavin Johnson + 2 more

cs.HC

TLDR

SpatialPrompt is an XR system enabling controllable 3D design by converting spatial sketches and voice prompts into executable AI constraints.

Key contributions

  • Transforms XR spatial sketches into executable constraints for controllable 3D generation.
  • Integrates 3D pen drawing with voice prompts for semantic and stylistic design intent.
  • Facilitates iterative refinement and synchronous co-creation in shared XR environments.
  • Implemented on Apple Vision Pro, showing intuitive workflow and shared understanding.

Why it matters

This paper introduces a novel XR approach to 3D design, making AI generation more controllable and collaborative. It simplifies complex 3D modeling by allowing intuitive spatial and voice input, enhancing shared understanding in co-creation.

Original Abstract

We present SpatialPrompt, an Extended Reality(XR) system that turns spatial sketches into executable constraints for controllable 3D generation. Users draw rough structures with a 3D pen and add voice prompts for semantic and stylistic intent. The system supports iterative refinement and synchronous co-creation in shared space with color-coded contributions. Implemented on Apple Vision Pro with Logitech Muse and Meshy, a heuristic evaluation suggests that the workflow is intuitive and supports shared understanding in collaborative creation, while revealing needs for faster generation and clearer feedback.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.