TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction

TL;DR

This paper introduces TSDF++, a novel multi-object map representation that enables simultaneous tracking and reconstruction of multiple dynamic objects in a scene, effectively handling occlusions and scaling better than previous methods.

Contribution

We propose a multi-object TSDF formulation that encodes multiple surfaces in a single volume, improving scalability and occlusion handling in dynamic scene reconstruction.

Findings

Accurately reconstructs occluded object surfaces

Maintains a single unified scene map

Outperforms standard TSDF in synthetic datasets

Abstract

The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction. Virtually all of the previous attempts to map multiple dynamic objects have evolved to store individual objects in separate reconstruction volumes and track the relative pose between them. While simple and intuitive, such formulation does not scale well with respect to the number of objects in the scene and introduces the need for an explicit occlusion handling strategy. In contrast, we propose a map representation that allows maintaining a single volume for the entire scene and all the objects therein. To this end, we introduce a novel multi-object TSDF formulation that can encode multiple object surfaces at any given location in the map. In a multiple dynamic object tracking and reconstruction scenario, our representation allows maintaining accurate reconstruction of surfaces even while they become temporarily occluded by other objects moving in their proximity. We evaluate the proposed TSDF++ formulation on a public synthetic dataset and demonstrate its ability to preserve reconstructions of occluded surfaces when compared to the standard TSDF map representation.