ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models

TL;DR

This paper introduces ZISVFM, a zero-shot object instance segmentation method for indoor robots that combines SAM and a self-supervised ViT to accurately segment unknown objects without extensive training.

Contribution

The novel framework leverages zero-shot capabilities of SAM and visual transformer features to improve unseen object segmentation in robotic environments.

Findings

Outperforms existing UOIS methods on benchmark datasets

Effective in complex hierarchical environments like cabinets and drawers

Operates without extensive annotated training data

Abstract

Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learningbased segmentation techniques require extensive annotated datasets, which are impractical for the diversity of objects encountered in real-world scenarios. Unseen Object Instance Segmentation (UOIS) methods aim to address this by training models on synthetic data to generalize to novel objects, but they often suffer from the simulation-to-reality gap. This paper proposes a novel approach (ZISVFM) for solving UOIS by leveraging the powerful zero-shot capability of the segment anything model (SAM) and explicit visual representations from a selfsupervised vision transformer (ViT). The proposed framework operates in three stages: (1) generating object-agnostic mask proposals from colorized depth images using SAM, (2) refining these proposals using attention-based features from the selfsupervised ViT to filter non-object masks, and (3) applying K-Medoids clustering to generate point prompts that guide SAM towards precise object segmentation. Experimental validation on two benchmark datasets and a self-collected dataset demonstrates the superior performance of ZISVFM in complex environments, including hierarchical settings such as cabinets, drawers, and handheld objects. Our source code is available at https://github.com/Yinmlmaoliang/zisvfm.