PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction

TL;DR

This paper introduces a zero-shot panoptic reconstruction approach from RGB-D images that leverages open-vocabulary instance segmentation, addressing partial labeling and instance association challenges without relying on pre-trained models or known 3D object bounding boxes.

Contribution

It proposes a novel method combining partial label propagation with 3D instance graph segmentation for zero-shot panoptic reconstruction in complex scenes.

Findings

Outperforms state-of-the-art on ScanNet V2 and KITTI-360 datasets.

Effectively propagates partial labels using dense generalized features.

Utilizes 3D scene geometry for robust instance association.

Abstract

Panoptic reconstruction is a challenging task in 3D scene understanding. However, most existing methods heavily rely on pre-trained semantic segmentation models and known 3D object bounding boxes for 3D panoptic segmentation, which is not available for in-the-wild scenes. In this paper, we propose a novel zero-shot panoptic reconstruction method from RGB-D images of scenes. For zero-shot segmentation, we leverage open-vocabulary instance segmentation, but it has to face partial labeling and instance association challenges. We tackle both challenges by propagating partial labels with the aid of dense generalized features and building a 3D instance graph for associating 2D instance IDs. Specifically, we exploit partial labels to learn a classifier for generalized semantic features to provide complete labels for scenes with dense distilled features. Moreover, we formulate instance association as a 3D instance graph segmentation problem, allowing us to fully utilize the scene geometry prior and all 2D instance masks to infer global unique pseudo 3D instance ID. Our method outperforms state-of-the-art methods on the indoor dataset ScanNet V2 and the outdoor dataset KITTI-360, demonstrating the effectiveness of our graph segmentation method and reconstruction network.