# ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking

arXiv: https://arxiv.org/abs/2105.04112 · HTML: https://mlsanity.com/paper/2105.04112/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2021.

## Built on by (most cited first, 22 of 22)

- [RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis](https://mlsanity.com/paper/2205.07058/) (2022)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images](https://mlsanity.com/paper/2212.09100/) (2022)
- [Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes](https://mlsanity.com/paper/2404.04557/) (2024)
- [XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity](https://mlsanity.com/paper/2506.00599/) (2025)
- [Next-Best-View Prediction for Active Stereo Cameras and Highly Reflective Objects](https://mlsanity.com/paper/2202.13263/) (2022)
- [Multi-View Keypoints for Reliable 6D Object Pose Estimation](https://mlsanity.com/paper/2303.16833/) (2023)
- [A Low-Cost, High-Speed, and Robust Bin Picking System for Factory Automation Enabled by a Non-Stop, Multi-View, and Active Vision Scheme](https://mlsanity.com/paper/2410.00706/) (2024)
- [Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames](https://mlsanity.com/paper/2503.03726/) (2025)
- [CenDerNet: Center and Curvature Representations for Render-and-Compare 6D Pose Estimation](https://mlsanity.com/paper/2208.09829/) (2022)
- [ZeroBP: Learning Position-Aware Correspondence for Zero-shot 6D Pose Estimation in Bin-Picking](https://mlsanity.com/paper/2502.01004/) (2025)
- [Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Camera](https://mlsanity.com/paper/2503.20207/) (2025)
- [Diffusion Suction Grasping with Large-Scale Parcel Dataset](https://mlsanity.com/paper/2502.07238/) (2025)
- [Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Clouds](https://mlsanity.com/paper/2512.07211/) (2025)
- [TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objects](https://mlsanity.com/paper/2607.21071/) (2026)
- [A High Resolution Multi-exposure Stereoscopic Image & Video Database of Natural Scenes](https://mlsanity.com/paper/2206.11095/) (2022)
- [Targeted Hard Sample Synthesis Based on Estimated Pose and Occlusion Error for Improved Object Pose Estimation](https://mlsanity.com/paper/2412.04279/) (2024)
- [MVTOP: Multi-View Transformer-based Object Pose-Estimation](https://mlsanity.com/paper/2508.03243/) (2025)
- [DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects](https://mlsanity.com/paper/2510.10933/) (2025)
- [SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking](https://mlsanity.com/paper/2512.08430/) (2025)
- [Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking](https://mlsanity.com/paper/2604.04690/) (2026)
- [DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception](https://mlsanity.com/paper/2608.31002/) (2026)

## Abstract (arXiv)

In robotic bin-picking applications, the perception of texture-less, highly reflective parts is a valuable but challenging task. The high glossiness can introduce fake edges in RGB images and inaccurate depth measurements especially in heavily cluttered bin scenario. In this paper, we present the ROBI (Reflective Objects in BIns) dataset, a public dataset for 6D object pose estimation and multi-view depth fusion in robotic bin-picking scenarios. The ROBI dataset includes a total of 63 bin-picking scenes captured with two active stereo camera: a high-cost Ensenso sensor and a low-cost RealSense sensor. For each scene, the monochrome/RGB images and depth maps are captured from sampled view spheres around the scene, and are annotated with accurate 6D poses of visible objects and an associated visibility score. For evaluating the performance of depth fusion, we captured the ground truth depth maps by high-cost Ensenso camera with objects coated in anti-reflective scanning spray. To show the utility of the dataset, we evaluated the representative algorithms of 6D object pose estimation and multi-view depth fusion on the full dataset. Evaluation results demonstrate the difficulty of highly reflective objects, especially in difficult cases due to the degradation of depth data quality, severe occlusions and cluttered scene. The ROBI dataset is available online at https://www.trailab.utias.utoronto.ca/robi.