用单目相机实现接近深度相机的精准建图与定位。
MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM
- 将高斯点云转为像素级深度和法向图，实现地图对位姿的闭环反馈。
- 通过自适应对齐深度先验，解决单目系统尺度漂移问题。
- 仅用单目图像达到与双目/深度相机相当的建图精度，适合移动设备使用。
实时单目同时定位与地图构建（SLAM）面临尺度模糊和缺乏几何自校正的问题。尽管3D高斯喷溅（3DGS）可实现高质量渲染，现有单目系统仍为开环设计：深度先验被注入建图过程，但优化后的几何信息无法有效纠正跟踪漂移。本文提出MyGO-Splat，一种闭环高斯SLAM框架，通过解析式将高斯原型光栅化为像素级深度和表面法向，使地图能够主动监督相机位姿优化。为弥合单目先验与尺度一致性，该框架引入感知尺度的自适应对齐机制，将基础模型的深度估计投影至全局优化的高斯空间，形成尺度反馈的自校正循环。大量实验表明，该闭环设计显著提升了尺度稳定性与外观-几何一致性，在仅使用单目输入的情况下，性能接近于RGB-D方法。
原文摘要 · Abstract (English)
Real-time monocular Simultaneous Localization and Mapping (SLAM) fundamentally suffers from scale ambiguity and a lack of geometric self-correction. While 3D Gaussian Splatting (3DGS) enables high-fidelity rendering, existing RGB-only systems remain open-loop because depth priors are injected into mapping but refined geometry cannot effectively regulate tracking drift. We present MyGO-Splat, a closed-loop Gaussian SLAM framework that analytically rasterizes Gaussian primitives into pixel-wise depth and surface normals, allowing the map to actively supervise camera pose optimization. To bridge monocular priors and scale consistency, our framework introduces scale-aware adaptive alignment that projects foundation-model depth estimates into the globally optimized Gaussian space, forming a self-correcting cycle for scale feedback. Extensive evaluations show that this closed-loop design improves scale stability and appearance-geometry consistency, achieving performance comparable to RGB-D methods while using only monocular input.
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。