ProDyG：基于单目视频高斯泼溅的渐进式动态场景重建
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
AI总结：
本文提出ProDyG，在SLAM系统中解耦静态与动态部分，结合运动掩蔽策略和Motion Scaffolds图的渐进式自适应，实现单目视频的在线动态场景重建，渲染与跟踪性能均达到领先水平。
摘要：
实现真正实用的动态三维重建需要在线运行、全局位姿与地图一致性、精细的外观建模，以及同时处理RGB和RGB-D输入的灵活性。然而，现有的SLAM方法通常仅移除动态部分或需要RGB-D输入，离线方法无法扩展到长视频序列，而当前基于Transformer的前馈方法缺乏全局一致性和外观细节。为此，我们通过在SLAM系统中解耦静态与动态部分来实现在线动态场景重建。位姿通过一种新颖的运动掩蔽策略进行鲁棒跟踪，动态部分则利用Motion Scaffolds图的渐进式自适应进行重建。我们的方法在新视角渲染方面可与离线方法相媲美，并在跟踪性能上与最先进的动态SLAM方法达到同等水平。
英文摘要：
Achieving truly practical dynamic 3D reconstruction requires online operation, global pose and map consistency, detailed appearance modeling, and the flexibility to handle both RGB and RGB-D inputs. However, existing SLAM methods typically merely remove the dynamic parts or require RGB-D input, while offline methods are not scalable to long video sequences, and current transformer-based feedforward methods lack global consistency and appearance details. To this end, we achieve online dynamic scene reconstruction by disentangling the static and dynamic parts within a SLAM system. The poses are tracked robustly with a novel motion masking strategy, and dynamic parts are reconstructed leveraging a progressive adaptation of a Motion Scaffolds graph. Our method yields novel view renderings competitive to offline methods and achieves on-par tracking with state-of-the-art dynamic SLAM methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
