用单目图像+UniDepth实现高精度三维重建与定位，无需深度传感器。
UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM
- 基于UniDepth估计单目深度，结合高斯点云优化场景与相机位姿
- 在TUM数据集上实现低至0.12的ATERMSE轨迹误差
- 适合移动机器人、AR/VR等无深度硬件的实时三维系统
近期单目神经深度估计进展，尤其是UniDepth网络的突破，推动了将其集成到高斯点云框架中用于单目SLAM的研究。本文提出UDGS-SLAM，一种新方法，可在不依赖RGB-D传感器的情况下完成高斯点云框架中的深度估计。该方法采用统计滤波确保深度估计的局部一致性，并联合优化相机位姿与高斯场景表示参数。所提方法生成高质量渲染图像，并在相机轨迹上实现低ATERMSE。在TUM RGB-D数据集上的严格评估表明，其在多种场景下均优于多个基线方法。此外，通过消融实验验证了设计选择的有效性，并研究了不同网络主干编码器对系统性能的影响。
原文摘要 · Abstract (English)
Recent advancements in monocular neural depth estimation, particularly those achieved by the UniDepth network, have prompted the investigation of integrating UniDepth within a Gaussian splatting framework for monocular SLAM. This study presents UDGS-SLAM, a novel approach that eliminates the necessity of RGB-D sensors for depth estimation within Gaussian splatting framework. UDGS-SLAM employs statistical filtering to ensure local consistency of the estimated depth and jointly optimizes camera trajectory and Gaussian scene representation parameters. The proposed method achieves high-fidelity rendered images and low ATERMSE of the camera trajectory. The performance of UDGS-SLAM is rigorously evaluated using the TUM RGB-D dataset and benchmarked against several baseline methods, demonstrating superior performance across various scenarios. Additionally, an ablation study is conducted to validate design choices and investigate the impact of different network backbone encoders on system performance.
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。