XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity

ICLR 2026 Conference Submission13930 Authors

Keywords: Dataset and Benchmarks, 6D Pose Estimation, Multi-instance 2D detection, Industrial Bin-picking, Clutter Scenes

TL;DR: A High-precision Benchmark for Robust 6D Object Pose Estimation under Real-World Industrial Complexity

Abstract:

We introduce XYZ-IBD, a bin-picking benchmark for 6D pose estimation that captures real-world industrial complexity, including challenging object geometries, reflective materials, severe occlusions, and dense clutter. The dataset reflects authentic robotic manipulation scenarios with millimeter-accurate annotations. Unlike existing datasets that primarily focus on household objects, which approach saturation, XYZ-IBD represents the unsolved vision problems in the real-world application. The dataset features metallic and mostly symmetrical objects of varying shapes and sizes. These objects are heavily occluded and randomly arranged in bins with high density, replicating the challenges of industrial bin-picking.
XYZ-IBD was collected using two high-precision industrial cameras and one commercially available camera, providing RGB, grayscale, and depth images. It contains 75 multi-view real-world scenes with around 273k annotated object instances, along with a large-scale synthetic dataset rendered under simulated bin-picking conditions. We employ a meticulous annotation pipeline that includes anti-reflection spray, multi-view depth fusion, and semi-automatic annotation, achieving millimeter-level pose labeling accuracy required for industrial manipulation. Quantification in simulated environments confirms the reliability of the ground-truth annotations.
We benchmark state-of-the-art methods on 2D detection and 6D pose estimation tasks on our dataset, revealing significant performance degradation in our setups compared to current academic household benchmarks. By capturing the complexity of real-world bin-picking scenarios, XYZ-IBD introduces more realistic and challenging vision problems for future research.

Primary Area: datasets and benchmarks

Submission Number: 13930