Real-time dense scene reconstruction during unstable camera motions is crucial for robotics, yet current RGB-D SLAM systems fail when cameras experience large viewpoint changes, fast motions, or sudden shaking. Classical optimization-based methods deliver high accuracy but fail with poor initialization during large motions, while learning-based approaches provide robustness but lack sufficient accuracy for dense reconstruction. We address this challenge through a combination of learning-based initialization with optimization-based refinement. Our method employs a camera pose regression network to predict metric-aware relative poses from consecutive RGB-D frames, which serve as reliable starting points for a randomized optimization algorithm that further aligns depth images with the scene geometry. Extensive experiments demonstrate promising results: our approach outperforms the best competitor on challenging benchmarks, while maintaining comparable accuracy on stable motion sequences. The system operates in real-time, showcasing that combining simple and principled techniques can achieve both robustness for unstable motions and accuracy for dense reconstruction. Code released: https://github.com/siyandong/PROFusion.

翻译：在相机运动不稳定的情况下实现实时稠密场景重建对机器人技术至关重要，然而当前的RGB-D SLAM系统在相机经历大视角变化、快速运动或突然抖动时会失效。基于经典优化的方法能提供高精度，但在大运动下因初始化不良而失败；而基于学习的方法虽具有鲁棒性，却缺乏稠密重建所需的足够精度。我们通过结合基于学习的初始化与基于优化的细化来解决这一挑战。我们的方法采用一个相机姿态回归网络，从连续的RGB-D帧中预测具有度量感知的相对姿态，这些姿态作为随机化优化算法的可靠起点，进一步将深度图像与场景几何对齐。大量实验证明了令人鼓舞的结果：我们的方法在具有挑战性的基准测试中优于最佳竞争对手，同时在稳定运动序列上保持相当的精度。该系统能够实时运行，表明结合简单且原理清晰的技术能够同时实现不稳定运动下的鲁棒性与稠密重建的精确性。代码已发布：https://github.com/siyandong/PROFusion。