Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling

TL;DR

This paper introduces a Hierarchical Occlusion Modeling scheme for unseen object amodal instance segmentation, enabling robots to perceive and manipulate occluded objects in cluttered environments, advancing robotic perception capabilities.

Contribution

The paper presents a novel Hierarchical Occlusion Modeling approach that improves unseen object amodal segmentation by reasoning about occlusions in a hierarchical manner.

Findings

Achieved state-of-the-art performance on three benchmarks.

Enabled robotic manipulation of occluded objects.

Provided open-source code and datasets for further research.

Abstract

Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment. Although previous works achieved encouraging results, they were limited to segmenting the only visible regions of unseen objects. For robotic manipulation in a cluttered scene, amodal perception is required to handle the occluded objects behind others. This paper addresses Unseen Object Amodal Instance Segmentation (UOAIS) to detect 1) visible masks, 2) amodal masks, and 3) occlusions on unseen object instances. For this, we propose a Hierarchical Occlusion Modeling (HOM) scheme designed to reason about the occlusion by assigning a hierarchy to a feature fusion and prediction order. We evaluated our method on three benchmarks (tabletop, indoors, and bin environments) and achieved state-of-the-art (SOTA) performance. Robot demos for picking up occluded objects, codes, and datasets are available at https://sites.google.com/view/uoais