Towards Deep Learning-based 6D Bin Pose Estimation in 3D Scans

TL;DR

This paper compares analytical and deep learning methods for 6D bin pose estimation in 3D scans, showing that augmenting training data improves neural model accuracy, with a focus on robustness and industry relevance.

Contribution

It introduces a new dataset of synthetic and real scans and evaluates two methods, highlighting the benefits of synthetic data augmentation for neural pose estimation.

Findings

Synthetic data augmentation improves neural model accuracy

Analytical methods are less robust and harder to update

Data-driven methods outperform traditional analytical approaches

Abstract

An automated robotic system needs to be as robust as possible and fail-safe in general while having relatively high precision and repeatability. Although deep learning-based methods are becoming research standard on how to approach 3D scan and image processing tasks, the industry standard for processing this data is still analytically-based. Our paper claims that analytical methods are less robust and harder for testing, updating, and maintaining. This paper focuses on a specific task of 6D pose estimation of a bin in 3D scans. Therefore, we present a high-quality dataset composed of synthetic data and real scans captured by a structured-light scanner with precise annotations. Additionally, we propose two different methods for 6D bin pose estimation, an analytical method as the industrial standard and a baseline data-driven method. Both approaches are cross-evaluated, and our experiments show that augmenting the training on real scans with synthetic data improves our proposed data-driven neural model. This position paper is preliminary, as proposed methods are trained and evaluated on a relatively small initial dataset which we plan to extend in the future.