SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending

TL;DR

SpaceBlender is a novel AI pipeline that creates context-rich, collaborative VR environments by blending users' physical surroundings into virtual spaces, enhancing familiarity for collaborative tasks.

Contribution

It introduces a new generative AI pipeline that transforms 2D images into 3D environments for VR collaboration, integrating physical context into virtual spaces.

Findings

Participants found SpaceBlender environments more familiar and contextually relevant.

The pipeline effectively supports collaborative VR tasks with enhanced environmental context.

Some complexities in generated environments can impact user focus.

Abstract

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.