This paper presents a collaborative implicit neural simultaneous localization
and mapping (SLAM) system with RGB-D image sequences, which consists of
complete front-end and back-end modules including odometry, loop detection,
sub-map fusion, and global refinement. In order to enable all these modules in
a unified framework, we propose a novel neural point based 3D scene
representation in which each point maintains a learnable neural feature for
scene encoding and is associated with a certain keyframe. Moreover, a
distributed-to-centralized learning strategy is proposed for the collaborative
implicit SLAM to improve consistency and cooperation. A novel global
optimization framework is also proposed to improve the system accuracy like
traditional bundle adjustment. Experiments on various datasets demonstrate the
superiority of the proposed method in both camera tracking and mapping.

本文介绍了一种利用 RGB-D 图像序列进行协作式隐式神经同步定位与地图生成（SLAM）系统，该系统包括完整的前端和后端模块，包括里程计、回环检测、子图融合和全局优化。为了在一个统一的框架中实现所有这些模块，我们提出了一种新颖的基于神经元的三维场景表示方法，其中每个点维护一个可学习的神经元特征用于场景编码，并与某个关键帧相关联。此外，我们提出了一种分布式至集中式学习策略，用于改进协作式隐式 SLAM 的一致性和合作性。还提出了一种新颖的全局优化框架，以提高系统精度，类似于传统的束调整。在各种数据集上的实验证明了该方法在相机跟踪和地图生成方面的优越性。

CP-SLAM：协作神经点云 SLAM 系统

CP-SLAM: Collaborative Neural Point-based SLAM System

We present an approach for 3D global human mesh recovery from monocular
videos recorded with dynamic cameras. Our approach is robust to severe and
long-term occlusions and tracks human bodies even when they go outside the
camera's field of view. To achieve this, we first propose a deep generative
motion infiller, which autoregressively infills the body motions of occluded
humans based on visible motions. Additionally, in contrast to prior work, our
approach reconstructs human meshes in consistent global coordinates even with
dynamic cameras. Since the joint reconstruction of human motions and camera
poses is underconstrained, we propose a global trajectory predictor that
generates global human trajectories based on local body movements. Using the
predicted trajectories as anchors, we present a global optimization framework
that refines the predicted trajectories and optimizes the camera poses to match
the video evidence such as 2D keypoints. Experiments on challenging indoor and
in-the-wild datasets with dynamic cameras demonstrate that the proposed
approach outperforms prior methods significantly in terms of motion infilling
and global mesh recovery.

本篇文章提出了一种能够从单目录像中实现三维全局人体网格恢复的方法，该方法具有鲁棒性，即使在面临严重和长期的遮挡时，也可以跟踪人体；同时，该方法可以在动态相机下，构建出一致的全局人体网格，这一方法也被称为 “深度生成运动填充器”。