Sim2Real Instance-Level Style Transfer for 6D Pose Estimation

TL;DR

This paper introduces a novel sim2real style transfer method that enhances synthetic data for 6D pose estimation by transferring styles at the instance level, significantly improving real-world performance.

Contribution

It presents a new instance-level style transfer technique for synthetic data, reducing domain gaps and improving 6D pose estimation accuracy without human intervention.

Findings

Significant improvement in pose estimation accuracy.

Enhanced realism of style-transferred images.

Effective pipeline from data collection to training.

Abstract

In recent years, synthetic data has been widely used in the training of 6D pose estimation networks, in part because it automatically provides perfect annotation at low cost. However, there are still non-trivial domain gaps, such as differences in textures/materials, between synthetic and real data. These gaps have a measurable impact on performance. To solve this problem, we introduce a simulation to reality (sim2real) instance-level style transfer for 6D pose estimation network training. Our approach transfers the style of target objects individually, from synthetic to real, without human intervention. This improves the quality of synthetic data for training pose estimation networks. We also propose a complete pipeline from data collection to the training of a pose estimation network and conduct extensive evaluation on a real-world robotic platform. Our evaluation shows significant improvement achieved by our method in both pose estimation performance and the realism of images adapted by the style transfer.