TransPose: A Transformer-based 6D Object Pose Estimation Network with Depth Refinement

TL;DR

TransPose is a Transformer-based 6D object pose estimation network that uses RGB images and a depth refinement module to achieve superior accuracy in robotics and agricultural applications.

Contribution

The paper introduces TransPose, a novel Transformer-based architecture with a lightweight depth estimation and refinement module for improved 6D pose estimation from RGB images.

Findings

Outperforms state-of-the-art methods in 6D pose estimation

Effective in fruit-picking robotic applications

Achieves higher accuracy with RGB-only input

Abstract

As demand for robotics manipulation application increases, accurate vision-based 6D pose estimation becomes essential for autonomous operations. Convolutional Neural Networks (CNNs) based approaches for pose estimation have been previously introduced. However, the quest for better performance still persists especially for accurate robotics manipulation. This quest extends to the Agri-robotics domain. In this paper, we propose TransPose, an improved Transformer-based 6D pose estimation with a depth refinement module. The architecture takes in only an RGB image as input with no additional supplementing modalities such as depth or thermal images. The architecture encompasses an innovative lighter depth estimation network that estimates depth from an RGB image using feature pyramid with an up-sampling method. A transformer-based detection network with additional prediction heads is proposed to directly regress the object's centre and predict the 6D pose of the target. A novel depth refinement module is then used alongside the predicted centers, 6D poses and depth patches to refine the accuracy of the estimated 6D pose. We extensively compared our results with other state-of-the-art methods and analysed our results for fruit-picking applications. The results we achieved show that our proposed technique outperforms the other methods available in the literature.