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
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
Fig. 1: Overview of the proposed approach. For the miniature (left), the camera directly measures depth at the miniature’s physical scale (about 1 m, blue). Applying the depth scaling of Section III-A rescales this to the full-scale range (about 2 m, red). The full-scale synthetic renders (middle) provide depth directly in this range. The scale equivalence between the miniature and the full-scale object is illustrated (right).
Fig. 2: Pipe geometries across data domains. Representative examples of each pipe type in the synthetic, miniature, and full-scale domains (top to bottom) for Bend-45, Straight, Tee, Lateral, Offset-45, and Offset-90 (left to right).
Fig. 3: Point cloud comparison across data types. Clean Sim, Noise Sim (synthetic data with the ToF noise model), Miniature (Real), Full Scale (Real), and Full Scale (Denoised) by the CDM, shown for Lateral and Tee.
Fig. 4: Qualitative 6D pose estimation results on real pipes. Green boxes denote the ground truth, while red and blue boxes show the inference results of the model trained on simulation data only (Simulation Only) and on simulation and miniature data (Ours), respectively. The left three columns show PVN3D and the right three show RDPN6D. The number in each image is the ADD-S error of that frame’s inference result.