用深度图生成多房间隐私保护数字孪生，跨视角对齐更一致。
MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments
- 基于扩散模型，通过多视角重叠对齐实现跨视图一致性建模。
- 添加更多重叠视角可降低去噪方差，提升生成质量，零额外训练。
- 适合需要高保真多房间重建的隐私敏感场景，如智能家居、建筑可视化。
我们提出一种基于扩散模型的方法，仅使用深度图像生成多房间室内环境的隐私保护数字孪生。核心是新颖的多视角重叠场景对齐与隐式一致性（MOSAIC）模型，该模型在概率意义上显式考虑同一场景内各视角间的依赖关系。MOSAIC通过多通道推理时优化机制运行，避免了传统全景方法中因顺序处理或单房间约束导致的误差累积。该方法无需额外训练即可扩展至复杂场景，并在加入更多重叠视角时，可证明降低去噪过程中的方差，从而提升生成质量。实验表明，MOSAIC在图像保真度指标上优于现有最优基线，在复杂多房间环境重建中表现卓越。相关资源与代码见 https://mosaic-cmubig.github.io
原文摘要 · Abstract (English)
We introduce a diffusion-based approach for generating privacy-preserving digital twins of multi-room indoor environments from depth images only. Central to our approach is a novel Multi-view Overlapped Scene Alignment with Implicit Consistency (MOSAIC) model that explicitly considers cross-view dependencies within the same scene in the probabilistic sense. MOSAIC operates through a multi-channel inference-time optimization that avoids error accumulation common in sequential or single-room constraints in panorama-based approaches. MOSAIC scales to complex scenes with zero extra training and provably reduces the variance during denoising process when more overlapping views are added, leading to improved generation quality. Experiments show that MOSAIC outperforms state-of-the-art baselines on image fidelity metrics in reconstructing complex multi-room environments. Resources and code are at https://mosaic-cmubig.github.io
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。