Scene-level Tracking and Reconstruction without Object Priors

TL;DR

This paper introduces a real-time system for tracking and reconstructing all visible objects in a scene without prior knowledge of their properties, enabling dynamic scene understanding for robotics.

Contribution

The proposed method uniquely segments and updates non-rigid objects in real-time without prior object information, unlike previous segmentation-dependent approaches.

Findings

Successfully tracks and reconstructs multiple rigid and non-rigid objects in real-time.

Handles topology changes dynamically during scene reconstruction.

Integrates seamlessly into robotics applications for manipulation tasks.

Abstract

We present the first real-time system capable of tracking and reconstructing, individually, every visible object in a given scene, without any form of prior on the rigidness of the objects, texture existence, or object category. In contrast with previous methods such as Co-Fusion and MaskFusion that first segment the scene into individual objects and then process each object independently, the proposed method dynamically segments the non-rigid scene as part of the tracking and reconstruction process. When new measurements indicate topology change, reconstructed models are updated in real-time to reflect that change. Our proposed system can provide the live geometry and deformation of all visible objects in a novel scene in real-time, which makes it possible to be integrated seamlessly into numerous existing robotics applications that rely on object models for grasping and manipulation. The capabilities of the proposed system are demonstrated in challenging scenes that contain multiple rigid and non-rigid objects.