MaskedFusion: Mask-based 6D Object Pose Estimation

TL;DR

MaskedFusion is a modular framework that uses object masks and RGB-D data to improve 6D object pose estimation accuracy, outperforming previous methods on standard datasets.

Contribution

It introduces a mask-based approach integrated into a modular pipeline for more accurate 6D pose estimation from RGB-D data.

Findings

Achieved 97.3% accuracy on LineMOD dataset

Reached 93.3% on YCB-Video dataset

Outperforms previous state-of-the-art methods

Abstract

MaskedFusion is a framework to estimate the 6D pose of objects using RGB-D data, with an architecture that leverages multiple sub-tasks in a pipeline to achieve accurate 6D poses. 6D pose estimation is an open challenge due to complex world objects and many possible problems when capturing data from the real world, e.g., occlusions, truncations, and noise in the data. Achieving accurate 6D poses will improve results in other open problems like robot grasping or positioning objects in augmented reality. MaskedFusion improves the state-of-the-art by using object masks to eliminate non-relevant data. With the inclusion of the masks on the neural network that estimates the 6D pose of an object we also have features that represent the object shape. MaskedFusion is a modular pipeline where each sub-task can have different methods that achieve the objective. MaskedFusion achieved 97.3% on average using the ADD metric on the LineMOD dataset and 93.3% using the ADD-S AUC metric on YCB-Video Dataset, which is an improvement, compared to the state-of-the-art methods. The code is available on GitHub (https://github.com/kroglice/MaskedFusion).