Skip to content
KAISTARRCARRC
Back to Publications

2025 · conference

RealityCrafter: User-guided Editable 3D Scene Generation from a Single Image in Mixed Reality

Adjunct Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology

DOI: 10.1145/3746058.3758405

Abstract

Figure 1: RealityCrafter creates an editable 3D scene driven by user speech from a single real-world image.Our system (a) takes a single image as input; (b) reconstructs it into a 3D scene; and (c) empowers users to author that space via voice commands and pointer interactions.

Citation

@inproceedings{kim2025realitycrafter,
  title = {RealityCrafter: User-guided Editable 3D Scene Generation from a Single Image in Mixed Reality},
  author = {Seokyoung Kim and Dooyoung Kim and Taejun Son and Woontack Woo},
  booktitle = {Adjunct Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology},
  year = {2025},
  doi = {10.1145/3746058.3758405}
}

Resources

Related research outputs

2026Edge-centric space rescaling method for dissimilar space registration and system therefor
미국 등록, 12555342 (2026-02-17)
2026Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality
IEEE VR 2026 / IEEE Transactions on Visualization and Computer Graphics
2026Mix3R: Zero-shot Interactive 3D Scene Reconstruction from a Single Image in Mixed Reality
ISMAR 2026 / IEEE Transactions on Visualization and Computer Graphics