SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending
Numan, Nels, Rajaram, Shwetha, Kumaravel, Balasaravanan Thoravi, Marquardt, Nicolai, Wilson, Andrew D.
–arXiv.org Artificial Intelligence
There is increased interest in using generative AI to create 3D spaces for Virtual Reality (VR) applications. However, today's models produce artificial environments, falling short of supporting collaborative tasks that benefit from incorporating the user's physical context. To generate environments that support VR telepresence, we introduce SpaceBlender, a novel pipeline that utilizes generative AI techniques to blend users' physical surroundings into unified virtual spaces. This pipeline transforms user-provided 2D images into context-rich 3D environments through an iterative process consisting of depth estimation, mesh alignment, and diffusion-based space completion guided by geometric priors and adaptive text prompts. In a preliminary within-subjects study, where 20 participants performed a collaborative VR affinity diagramming task in pairs, we compared SpaceBlender with a generic virtual environment and a state-of-the-art scene generation framework, evaluating its ability to create virtual spaces suitable for collaboration. Participants appreciated the enhanced familiarity and context provided by SpaceBlender but also noted complexities in the generative environments that could detract from task focus. Drawing on participant feedback, we propose directions for improving the pipeline and discuss the value and design of blended spaces for different scenarios.
arXiv.org Artificial Intelligence
Sep-20-2024
- Country:
- North America
- United States
- Michigan (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.06)
- New York > New York County
- New York City (0.05)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe
- Germany > Hamburg (0.04)
- United Kingdom (0.04)
- Spain (0.04)
- France > Île-de-France
- Asia
- Japan > Honshū
- Kantō
- Tokyo Metropolis Prefecture > Tokyo (0.14)
- Ibaraki Prefecture > Tsukuba (0.04)
- Kansai > Osaka Prefecture
- Osaka (0.04)
- Kantō
- China > Yunnan Province
- Kunming (0.04)
- Japan > Honshū
- North America
- Genre:
- Research Report
- New Finding (0.93)
- Experimental Study (0.68)
- Research Report
- Industry:
- Health & Medicine > Therapeutic Area (0.46)
- Education (0.46)
- Technology:
- Information Technology
- Sensing and Signal Processing > Image Processing (1.00)
- Communications > Collaboration (1.00)
- Human Computer Interaction > Interfaces
- Virtual Reality (1.00)
- Artificial Intelligence
- Vision (1.00)
- Natural Language (1.00)
- Machine Learning > Neural Networks
- Deep Learning > Generative AI (0.54)
- Information Technology