用单目视频实时重建高保真3D场景，细节更清晰、结构更一致。
Monocular Online Reconstruction with Enhanced Detail Preservation
- 分层管理高斯点分布，无需深度图支持
- 多级占据哈希体提升细节与整体结构精度
- 兼容多种追踪系统，适合实时三维重建应用
我们提出一种基于3D高斯的在线密集映射框架，从单目图像流中重建逼真的细节。针对单目在线重建中的两大挑战——不依赖深度图分布高斯点，以及保持局部与全局一致性——我们引入两个核心模块：分层高斯管理模块实现高效高斯分布，全局一致性优化模块在所有尺度上维持对齐与连贯性。此外，我们设计了多级占据哈希体（MOHV），通过多粒度正则化机制捕捉精细与粗粒度几何与纹理，既保留复杂细节又维持整体结构完整性。相比最先进的纯RGB方法乃至RGB-D方法，本框架在重建质量上表现更优且计算效率更高，同时可无缝集成于多种追踪系统，具备良好的通用性与可扩展性。
原文摘要 · Abstract (English)
We propose an online 3D Gaussian-based dense mapping framework for photorealistic details reconstruction from a monocular image stream. Our approach addresses two key challenges in monocular online reconstruction: distributing Gaussians without relying on depth maps and ensuring both local and global consistency in the reconstructed maps. To achieve this, we introduce two key modules: the Hierarchical Gaussian Management Module for effective Gaussian distribution and the Global Consistency Optimization Module for maintaining alignment and coherence at all scales. In addition, we present the Multi-level Occupancy Hash Voxels (MOHV), a structure that regularizes Gaussians for capturing details across multiple levels of granularity. MOHV ensures accurate reconstruction of both fine and coarse geometries and textures, preserving intricate details while maintaining overall structural integrity. Compared to state-of-the-art RGB-only and even RGB-D methods, our framework achieves superior reconstruction quality with high computational efficiency. Moreover, it integrates seamlessly with various tracking systems, ensuring generality and scalability.
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。