DynaGSLAM：面向动态场景中运动物体在线渲染、跟踪与运动预测的实时高斯泼溅 SLAM
DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes
AI总结：
针对动态场景中运动物体会破坏 GS-SLAM 静态假设的问题，提出实时 DynaGSLAM，联合实现自身运动估计及运动物体的在线渲染、跟踪与预测，并在三个真实数据集上优于现有方法。
摘要：
同时定位与地图构建（SLAM）是计算机视觉、机器人以及自动驾驶汽车/无人机领域最重要的环境感知与导航算法之一。因此，高质量且快速的建图成为一个基础性问题。随着 3D Gaussian Splatting（3DGS）作为一种兼具出色渲染质量和速度的显式表示出现，最先进（SOTA）工作将 GS 引入 SLAM。与经典点云 SLAM 相比，GS-SLAM 通过从输入相机视图中学习来生成光度信息，并合成具有高质量纹理的未观测视图。然而，当运动物体占据场景、违背光束法平差的静态假设时，这些 GS-SLAM 会失效。运动 GS 的失败更新会影响静态 GS，并在较长帧序列中污染整张地图。尽管同期工作已作出一些努力以在 GS-SLAM 中考虑运动物体，但它们只是检测运动区域并将其从 GS 渲染中移除（即“反”动态 GS-SLAM），其中只有静态背景能够受益于 GS。为此，我们提出首个实时 GS-SLAM“DynaGSLAM”，可在联合估计准确自身运动的同时，实现动态场景中运动物体的高质量在线 GS 渲染、跟踪和运动预测。我们的 DynaGSLAM 在三个动态真实数据集上优于 SOTA 静态与“反”动态 GS-SLAM，同时在实践中保持速度和内存效率。
英文摘要：
Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones. Hence, high quality and fast mapping becomes a fundamental problem. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, state-of-the-art (SOTA) works introduce GS to SLAM. Compared to classical pointcloud-SLAM, GS-SLAM generates photometric information by learning from input camera views and synthesize unseen views with high-quality textures. However, these GS-SLAM fail when moving objects occupy the scene that violate the static assumption of bundle adjustment. The failed updates of moving GS affects the static GS and contaminates the full map over long frames. Although some efforts have been made by concurrent works to consider moving objects for GS-SLAM, they simply detect and remove the moving regions from GS rendering ("anti'' dynamic GS-SLAM), where only the static background could benefit from GS. To this end, we propose the first real-time GS-SLAM, "DynaGSLAM'', that achieves high-quality online GS rendering, tracking, motion predictions of moving objects in dynamic scenes while jointly estimating accurate ego motion. Our DynaGSLAM outperforms SOTA static & "Anti'' dynamic GS-SLAM on three dynamic real datasets, while keeping speed and memory efficiency in practice.
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。
