Recurrent Multi-View Collaborative Registration Network for 3D Reconstruction and Optical Measurement of Blade Profiles

Aligning multiple viewpoints to reconstruct a complete profile is crucial for the three-dimensional optical measurement of blade profiles. As foundational solutions, rigid pairwise point cloud registration methods often struggle to produce satisfactory results due to significant cumulative errors stemming from pairwise registration errors, while current multi-view registration methods also face challenges when their prerequisites conflict with the practical measurement scenarios of blade profiles. To address these issues, this study proposes a learning framework to recover a transformation vector between the coordinate frames of both the optical sensor and the rotational axis in our developed optical measurement system based on extracted adaptive feature embeddings from the initial coordinate representation of viewpoints, which simultaneously aligns all viewpoints into a complete profile without relying on any prerequisites. Furthermore, an elaborate recurrent updating strategy is incorporated into the framework that enables incremental refinement of the transformation vector, thus aiding the framework in meeting the high-precision measurement requirements at the 0.01mm level. Experimental results from both theoretical and real-world data, conducted on three representative blades and compared against nine state-of-the-art algorithms, consistently demonstrate the superiority of the proposed method in terms of accuracy, time efficiency, and robustness. The source code is available at https://github.com/Clarkxielf/Recurrent-Multi-View-Collaborative-Registration-Network.