Exploring 6D Object Pose Estimation with Deformation

TL;DR

DeSOPE introduces a comprehensive dataset for 6D object pose estimation considering deformations, highlighting the need for more robust methods in practical scenarios.

Contribution

The paper presents DeSOPE, a large-scale dataset with high-fidelity scans and pose annotations for deformed objects, addressing a gap in existing 6D pose estimation research.

Findings

Performance of pose methods drops with increased deformation.

Deformation significantly impacts pose estimation accuracy.

The dataset enables development of more robust pose estimation algorithms.

Abstract

We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption that fails in practice as objects deviate from their canonical shapes due to wear, impact, or deformation. To model this, we introduce the DeSOPE dataset, which features high-fidelity 3D scans of 26 common object categories, each captured in one canonical state and three deformed configurations, with accurate 3D registration to the canonical mesh. Additionally, it features an RGB-D dataset with 133K frames across diverse scenarios and 665K pose annotations produced via a semi-automatic pipeline. We begin by annotating 2D masks for each instance, then compute initial poses using an object pose method, refine them through an object-level SLAM system, and finally perform manual verification to produce the final annotations. We evaluate several object pose methods and find that performance drops sharply with increasing deformation, suggesting that robust handling of such deformations is critical for practical applications.