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

TL;DR

PoseFusion2 introduces a real-time SLAM system that simultaneously reconstructs static backgrounds and dynamic human shapes, including pose estimation, operating efficiently on GPUs.

Contribution

It presents a novel learning-based human detector integrated into a real-time SLAM framework for dynamic environments with moving humans.

Findings

Runs at ~26 fps for environment mapping.

Achieves up to 10 fps for human pose and shape estimation.

Effectively reconstructs static backgrounds and dynamic human meshes.

Abstract

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.