# PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time

arXiv: https://arxiv.org/abs/2108.00695 · HTML: https://mlsanity.com/paper/2108.00695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 2 Aug 2021.

## Builds on (most cited first, 13 of 13)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans](https://mlsanity.com/paper/2002.06289/) (2020)
- [DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes](https://mlsanity.com/paper/1806.05620/) (2018)
- [Generating 3D People in Scenes without People](https://mlsanity.com/paper/1912.02923/) (2019)
- [SurfelWarp: Efficient Non-Volumetric Single View Dynamic Reconstruction](https://mlsanity.com/paper/1904.13073/) (2019)
- [Multimotion Visual Odometry (MVO): Simultaneous Estimation of Camera and Third-Party Motions](https://mlsanity.com/paper/1808.00274/) (2018)
- [SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes](https://mlsanity.com/paper/2007.02108/) (2020)

## Abstract (arXiv)

Dynamic environments that include unstructured moving objects pose a hard problem for Simultaneous Localization and Mapping (SLAM) performance. The motion of rigid objects can be typically tracked by exploiting their texture and geometric features. However, humans moving in the scene are often one of the most important, interactive targets - they are very hard to track and reconstruct robustly due to non-rigid shapes. In this work, we present a fast, learning-based human object detector to isolate the dynamic human objects and realise a real-time dense background reconstruction framework. We go further by estimating and reconstructing the human pose and shape. The final output environment maps not only provide the dense static backgrounds but also contain the dynamic human meshes and their trajectories. Our Dynamic SLAM system runs at around 26 frames per second (fps) on GPUs, while additionally turning on accurate human pose estimation can be executed at up to 10 fps.