单目视频下实时重建动态场景，分离静态与动态部分。
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
- 在SLAM中分离静态与动态物体，实现在线重建。
- 新运动遮蔽策略提升姿态跟踪鲁棒性，动态部分渐进重构。
- 适合需要实时动态场景建模的研究者与开发者。
实现真正实用的动态3D重建需具备在线运行、全局位姿与地图一致性、细节外观建模能力，以及对RGB和RGB-D输入的灵活性。然而，现有SLAM方法通常仅移除动态物体或依赖RGB-D输入，而离线方法难以扩展至长视频序列，当前基于Transformer的前馈方法缺乏全局一致性与外观细节。为此，我们通过在SLAM系统中解耦静态与动态部分，实现了在线动态场景重建。采用新型运动遮蔽策略稳健地追踪位姿，利用运动骨架图的渐进适应重构动态部分。本方法生成的新视角渲染效果媲美离线方法，姿态跟踪性能与最先进动态SLAM方法相当。
原文摘要 · Abstract (English)
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.
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。