IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and tools

TL;DR

IndustryShapes is a comprehensive RGB-D dataset tailored for 6D pose estimation of industrial tools and components, providing realistic scenarios and challenging object types to advance robotics applications in manufacturing.

Contribution

The paper introduces IndustryShapes, the first dataset with RGB-D static onboarding sequences for industrial objects, bridging the gap between lab research and real-world deployment.

Findings

State-of-the-art methods show room for improvement on this dataset.

The dataset includes diverse scenes with multiple objects and challenging properties.

Evaluation highlights the need for more robust 6D pose estimation approaches.

Abstract

We introduce IndustryShapes, a new RGB-D benchmark dataset of industrial tools and components, designed for both instance-level and novel object 6D pose estimation approaches. The dataset provides a realistic and application-relevant testbed for benchmarking these methods in the context of industrial robotics bridging the gap between lab-based research and deployment in real-world manufacturing scenarios. Unlike many previous datasets that focus on household or consumer products or use synthetic, clean tabletop datasets, or objects captured solely in controlled lab environments, IndustryShapes introduces five new object types with challenging properties, also captured in realistic industrial assembly settings. The dataset has diverse complexity, from simple to more challenging scenes, with single and multiple objects, including scenes with multiple instances of the same object and it is organized in two parts: the classic set and the extended set. The classic set includes a total of 4,6k images and 6k annotated poses. The extended set introduces additional data modalities to support the evaluation of model-free and sequence-based approaches. To the best of our knowledge, IndustryShapes is the first dataset to offer RGB-D static onboarding sequences. We further evaluate the dataset on a representative set of state-of-the art methods for instance-based and novel object 6D pose estimation, including also object detection, segmentation, showing that there is room for improvement in this domain. The dataset page can be found in https://pose-lab.github.io/IndustryShapes.