PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation

TL;DR

This paper introduces PFRL, a reinforcement learning method that estimates 6D object poses from single RGB images without requiring ground-truth 6D annotations, reducing data collection costs.

Contribution

It formulates 6D pose refinement as a Markov Decision Process and employs weakly-supervised reinforcement learning with only 2D annotations.

Findings

Achieves state-of-the-art results on LINEMOD dataset.

Outperforms methods requiring full 6D annotations.

Demonstrates effective pose estimation without expensive ground-truth labels.

Abstract

6D pose estimation from a single RGB image is a challenging and vital task in computer vision. The current mainstream deep model methods resort to 2D images annotated with real-world ground-truth 6D object poses, whose collection is fairly cumbersome and expensive, even unavailable in many cases. In this work, to get rid of the burden of 6D annotations, we formulate the 6D pose refinement as a Markov Decision Process and impose on the reinforcement learning approach with only 2D image annotations as weakly-supervised 6D pose information, via a delicate reward definition and a composite reinforced optimization method for efficient and effective policy training. Experiments on LINEMOD and T-LESS datasets demonstrate that our Pose-Free approach is able to achieve state-of-the-art performance compared with the methods without using real-world ground-truth 6D pose labels.