cs.RONov 11, 2026

MiniPose: Miniature-Based Real Data Collection for 6D Pose Estimation of Large Industrial Pipe Segments

Authors: Hyunjun Kim, Youngjin Seo, Sungwon Seo, Jiyou Shin, Kunwoo Kim, Chanyong Park, Hyungpil Moon

Organizations: The authors are with the Faculty of Intelligent Robotics, Sungkyunkwan University, Suwon 2066, South Korea · The authors are with the Faculty of Mechanical Engineering, Sungkyunkwan University, Suwon 2066, South Korea

Abstract

6-DOF pose estimation of large and heavy industrial objects, such as large piping systems in shipyards and structural components in petrochemical plants, remains relatively underexplored in robotic perception. Repeatedly repositioning large objects is physically and spatially demanding, making it difficult to acquire real training data with sufficient pose diversity. Synthetic data offer a scalable alternative, but faithfully reproducing real RGB-D observations, particularly the structured measurement errors of real depth sensors, remains difficult. We propose MiniPose, a practical pipeline for miniature-based real RGB-D data collection that addresses both the data-acquisition burden and the sim-to-real gap. We fabricate a scaled-down replica and capture RGB-D data of it in diverse poses using a real RGB-D camera. RGB images are used directly, while depth maps are converted to a geometrically consistent representation of the full-scale object via a simple inverse scaling transformation. This allows training to incorporate real appearance and sensor measurement characteristics that are difficult to reproduce using synthetic data alone. To examine whether the benefit depends on a particular network, we evaluate two RGB-D pose estimators with different formulations, PVN3D and RDPN6D. Mixing at most 1,000 miniature images per pipe type, less than 10% of the training data, with 10,000 synthetic images improves the mean ADD-S AUC across pipe types over synthetic-only training for both estimators. A comparison with training on full-scale real data further suggests that miniature data can serve as a proxy where full-scale collection is difficult, reducing the data-collection burden for large industrial objects.

Figures & tables

Explore similar work

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

    May 31, 2025Junwen Huang, Jiaqi Hu, Peter KT Yu +3Object Pose EstimationRobotic Manipulation

  2. G6D: Geometric Learning-Free RGB-D 6D Pose Solver for Robotic Manipulation

    Sep 20, 2026Yixuan Liang, William Chen, Yunan Wang +4Object Pose EstimationRobotic Manipulation

  3. Exploring 6D Object Pose Estimation with Deformation

    Apr 8, 2026Zhiqiang Liu, Rui Song, Duanmu Chuangqi +3Object Pose Estimation