SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design
arXiv:2605.07894 · doi:10.1145/3802974.3809475
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.