SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910201792167936 |
|---|---|
| author | Yu, Yichen Andy Li, Wanru Wang, Qiaoran Ross, Jymon Johnson, Gavin Lui, Mandy Jin, Qiao |
| author_facet | Yu, Yichen Andy Li, Wanru Wang, Qiaoran Ross, Jymon Johnson, Gavin Lui, Mandy Jin, Qiao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07894 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design Yu, Yichen Andy Li, Wanru Wang, Qiaoran Ross, Jymon Johnson, Gavin Lui, Mandy Jin, Qiao Human-Computer Interaction 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. |
| title | SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.07894 |