# Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Camera

arXiv: https://arxiv.org/abs/2503.20207 · HTML: https://mlsanity.com/paper/2503.20207/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction](https://mlsanity.com/paper/2205.15848/) (2022)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence](https://mlsanity.com/paper/2311.14155/) (2023)
- [NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields](https://mlsanity.com/paper/2203.01913/) (2022)
- [Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions](https://mlsanity.com/paper/2203.17234/) (2022)
- [MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion](https://mlsanity.com/paper/2004.04336/) (2020)
- [ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers](https://mlsanity.com/paper/2309.11986/) (2023)
- [Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives](https://mlsanity.com/paper/2201.11736/) (2022)
- [Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2203.10339/) (2022)
- [TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2212.12902/) (2022)
- [ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking](https://mlsanity.com/paper/2105.04112/) (2021)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [Gaussians on Riemannian Manifolds: Applications for Robot Learning and Adaptive Control](https://mlsanity.com/paper/1909.05946/) (2019)
- [Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects](https://mlsanity.com/paper/2203.08472/) (2022)
- [Object Pose Estimation via the Aggregation of Diffusion Features](https://mlsanity.com/paper/2403.18791/) (2024)
- [LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration](https://mlsanity.com/paper/2103.15039/) (2021)
- [Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2308.10016/) (2023)
- [Next-Best-View Prediction for Active Stereo Cameras and Highly Reflective Objects](https://mlsanity.com/paper/2202.13263/) (2022)
- [Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation](https://mlsanity.com/paper/2311.09500/) (2023)

## Built on by (most cited first, 2 of 2)

- [DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects](https://mlsanity.com/paper/2510.10933/) (2025)
- [Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking](https://mlsanity.com/paper/2604.04690/) (2026)

## Abstract (arXiv)

Bin-picking of metal objects using low-cost RGB-D cameras often suffers from sparse depth information and reflective surface textures, leading to errors and the need for manual labeling. To reduce human intervention, we propose a two-stage framework consisting of a metric learning stage and a self-training stage. Specifically, to automatically process data captured by a low-cost camera (LC), we introduce a Multi-object Pose Reasoning (MoPR) algorithm that optimizes pose hypotheses under depth, collision, and boundary constraints. To further refine pose candidates, we adopt a Symmetry-aware Lie-group based Bayesian Gaussian Mixture Model (SaL-BGMM), integrated with the Expectation-Maximization (EM) algorithm, for symmetry-aware filtering. Additionally, we propose a Weighted Ranking Information Noise Contrastive Estimation (WR-InfoNCE) loss to enable the LC to learn a perceptual metric from reconstructed data, supporting self-training on untrained or even unseen objects. Experimental results show that our approach outperforms several state-of-the-art methods on both the ROBI dataset and our newly introduced Self-ROBI dataset.