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

2026-02-05

AI Summary

Existing 6D object pose estimation datasets are largely confined to household objects or synthetic scenes, lacking benchmarks tailored to real-world industrial assembly environments. To address this gap, this work introduces IndustryShapes, a dataset captured in authentic industrial settings using RGB-D sensors, featuring five challenging categories of tools and components. It includes complex configurations such as single/multiple objects and multiple instances of the same type, organized into a core set (4,600 images with 6,000 pose annotations) and an extended set incorporating additional modalities. IndustryShapes is the first to provide static on-line sequence data for industrial applications, supporting both instance-level and novel-object 6D pose estimation, and enabling evaluation of model-agnostic and sequential methods. Benchmark results reveal substantial room for improvement among current state-of-the-art approaches, effectively bridging the gap between laboratory research and real-world manufacturing deployment.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

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.

Problem

• 6D object pose estimation
• industrial robotics
• RGB-D dataset
• benchmark
• manufacturing scenarios

Innovation

• RGB-D dataset
• 6D object pose estimation
• industrial robotics
• novel object pose estimation
• static onboarding sequences