SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design
For collaborative 3D design, this system provides a novel interface for spatial intent expression, though the evaluation is preliminary and incremental over existing sketch-based methods.
SpatialPrompt enables users to express spatial intent through XR sketches and voice, converting them into constraints for AI 3D generation, with heuristic evaluation showing intuitive workflow but needing faster generation.
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.