EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach

TL;DR

EfficientPose is a fast, accurate, and scalable end-to-end method for 6D object pose estimation that detects multiple objects and their full poses simultaneously, outperforming previous approaches in accuracy and speed.

Contribution

The paper introduces EfficientPose, a novel single-shot approach for multi-object 6D pose estimation that combines detection and pose estimation efficiently, with a new augmentation technique for improved generalization.

Findings

Achieves 97.35% accuracy on Linemod dataset

Runs at over 27 FPS for single object detection

Handles multiple objects simultaneously with over 26 FPS

Abstract

In this paper we introduce EfficientPose, a new approach for 6D object pose estimation. Our method is highly accurate, efficient and scalable over a wide range of computational resources. Moreover, it can detect the 2D bounding box of multiple objects and instances as well as estimate their full 6D poses in a single shot. This eliminates the significant increase in runtime when dealing with multiple objects other approaches suffer from. These approaches aim to first detect 2D targets, e.g. keypoints, and solve a Perspective-n-Point problem for their 6D pose for each object afterwards. We also propose a novel augmentation method for direct 6D pose estimation approaches to improve performance and generalization, called 6D augmentation. Our approach achieves a new state-of-the-art accuracy of 97.35% in terms of the ADD(-S) metric on the widely-used 6D pose estimation benchmark dataset Linemod using RGB input, while still running end-to-end at over 27 FPS. Through the inherent handling of multiple objects and instances and the fused single shot 2D object detection as well as 6D pose estimation, our approach runs even with multiple objects (eight) end-to-end at over 26 FPS, making it highly attractive to many real world scenarios. Code will be made publicly available at https://github.com/ybkscht/EfficientPose.