Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models

2026-06-15

AI Summary

This work addresses the challenge of pose estimation for industrial object point clouds in the absence of known 3D models by proposing a model-free method that leverages rotational symmetry as a geometric prior. The approach explicitly incorporates rotational symmetry constraints into an iterative optimization framework to jointly estimate object pose and refine the input point cloud. It first identifies symmetric correspondences via nearest-neighbor search and then constructs a symmetry-aware loss function to guide the optimization process. To the best of our knowledge, this is the first model-free method to explicitly model rotational symmetry, enabling robust cross-category generalization. Evaluated on a dataset comprising four categories of synthetic objects and real-world wheel hubs, the method achieves performance comparable to state-of-the-art approaches that rely on accurate 3D models.

Abstract

Object pose estimation is crucial to many industrial applications, with one example being automated spray painting using a robot. However, confidentiality concerns often limit access to high-quality 3D models, posing a significant challenge for point-cloud-based pose estimation. In such scenarios, rotational symmetry, a readily accessible characteristic of many industrial objects, can provide valuable prior information to facilitate pose estimation.In this paper, we propose a method that leverages the rotational symmetry commonly found in industrial objects to address the challenge caused by the absence of 3D models. The object pose is jointly estimated with point cloud refinement through an iterative optimization process. This optimization relies on a rotational symmetry constraint loss. To construct this loss, each 3D point is rotated according to the currently estimated pose, and multiple correspondences are identified using nearest-neighbor search by exploiting the rotational symmetry property. These correspondences are then used to compute the rotational symmetry constraint loss, which iteratively refines both the pose and the point cloud.By explicitly incorporating rotational symmetry into the optimization process, the proposed method achieves robust pose estimation and generalizes well across diverse object types. The proposed method is evaluated on a dataset specifically created for point clouds without known 3D models, consisting of four categories of synthetic objects and one real wheel hub collected from a production line. Experimental results demonstrate that the proposed method achieves performance comparable to methods that rely on known 3D models.

Problem

• pose estimation
• point clouds
• rotational symmetry
• 3D models
• industrial objects

Innovation

• rotational symmetry
• pose estimation
• point cloud
• model-free
• iterative optimization