3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances

TL;DR

This paper introduces an unsupervised method for discovering, reconstructing, and localizing multiple identical 3D objects within a single RGB-D image, without relying on segmentation or prior scene knowledge.

Contribution

The proposed approach automatically finds recurrent object patterns in a single RGB-D image using appearance and geometry, enabling scalable 3D object modeling without supervision.

Findings

Successfully discovers multiple object instances in RGB-D images.

Generates compact and descriptive 3D object models.

Demonstrates application in robotic object picking scenarios.

Abstract

Unsupervised object modeling is important in robotics, especially for handling a large set of objects. We present a method for unsupervised 3D object discovery, reconstruction, and localization that exploits multiple instances of an identical object contained in a single RGB-D image. The proposed method does not rely on segmentation, scene knowledge, or user input, and thus is easily scalable. Our method aims to find recurrent patterns in a single RGB-D image by utilizing appearance and geometry of the salient regions. We extract keypoints and match them in pairs based on their descriptors. We then generate triplets of the keypoints matching with each other using several geometric criteria to minimize false matches. The relative poses of the matched triplets are computed and clustered to discover sets of triplet pairs with similar relative poses. Triplets belonging to the same set are likely to belong to the same object and are used to construct an initial object model. Detection of remaining instances with the initial object model using RANSAC allows to further expand and refine the model. The automatically generated object models are both compact and descriptive. We show quantitative and qualitative results on RGB-D images with various objects including some from the Amazon Picking Challenge. We also demonstrate the use of our method in an object picking scenario with a robotic arm.