vMAP: Vectorised Object Mapping for Neural Field SLAM
vMAP: Vectorised Object Mapping for Neural Field SLAM
复制标题
DOI：
10.1109/cvpr52729.2023.00098
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Xin Kong;Shikun Liu;Marwan Taher;A. Davison
中科院分区：
文献类型：
--
作者：
Xin Kong;Shikun Liu;Marwan Taher;A. Davison
我们提出了vMAP，一个对象级的密集SLAM系统，使用神经场表示。每个对象都由一个小的MLP表示，从而实现高效，防水的对象建模，而无需3D先验。当RGB-D摄像机在没有先验信息的情况下浏览场景时，vMAP会动态检测对象实例，并将其动态添加到其地图中。具体而言，由于矢量化训练的强大功能，vMAP可以优化单个场景中多达50个单独的对象，并且具有5 Hz地图更新的极其高效的训练速度。我们的实验表明，显着提高场景级和对象级的重建质量相比，以前的神经场SLAM系统。项目页面：https://kxhit.github.io/vMAP。
We present vMAP, an object-level dense SLAM system using neural field representations. Each object is repre-sented by a small MLP, enabling efficient, watertight object modelling without the needfor 3D priors. As an RGB-D camera browses a scene with no prior in-formation, vMAP detects object instances on-the-fly, and dynamically adds them to its map. Specifically, thanks to the power of vectorised training, vMAP can optimise as many as 50 individual objects in a single scene, with an extremely efficient training speed of 5Hz map update. We experimentally demonstrate significantly improved scene-level and object-level reconstruction quality compared to prior neural field SLAM systems. Project page: https://kxhit.github.io/vMAP.