3D Indoor Instance Segmentation in an Open-World

TL;DR

This paper introduces a novel open-world 3D indoor instance segmentation approach that can identify known and unknown objects, incrementally learn new categories, and employs auto-labeling and probability adjustment techniques to improve performance.

Contribution

It pioneers open-world 3D instance segmentation, proposing auto-labeling, pseudo-label refinement, and new dataset splits for realistic indoor scene scenarios.

Findings

Effective separation of known and unknown categories.

Improved pseudo-label quality at inference.

Promising performance in open-world segmentation tasks.

Abstract

Existing 3D instance segmentation methods typically assume that all semantic classes to be segmented would be available during training and only seen categories are segmented at inference. We argue that such a closed-world assumption is restrictive and explore for the first time 3D indoor instance segmentation in an open-world setting, where the model is allowed to distinguish a set of known classes as well as identify an unknown object as unknown and then later incrementally learning the semantic category of the unknown when the corresponding category labels are available. To this end, we introduce an open-world 3D indoor instance segmentation method, where an auto-labeling scheme is employed to produce pseudo-labels during training and induce separation to separate known and unknown category labels. We further improve the pseudo-labels quality at inference by adjusting the unknown class probability based on the objectness score distribution. We also introduce carefully curated open-world splits leveraging realistic scenarios based on inherent object distribution, region-based indoor scene exploration and randomness aspect of open-world classes. Extensive experiments reveal the efficacy of the proposed contributions leading to promising open-world 3D instance segmentation performance.