A two-stage learning framework with a beam image dataset for automatic laser resonator alignment

• First beam image dataset capturing diverse optical-alignment patterns and parameters • Optical resonator alignment cast as a pairwise beam-pattern regression task • Two-stage model with both feature interaction and refinement for coarse-to-fine alignment • Trained on one device, the model generalizes to another without re-training • Achieves high accuracy with real-time inference on embedded edge hardware Accurate alignment of a laser resonator is essential for upscaling industrial laser manufacturing and precision processing. However, traditional manual or semi-automatic methods depend heavily on operator expertise, and struggle with the interdependence among multiple alignment parameters. To tackle this, we introduce the first real-world image dataset for automatic laser resonator alignment, collected on a laboratory-built resonator setup. It comprises over 6,000 beam profiler images annotated with four key alignment parameters (intracavity iris aperture diameter, output coupler pitch and yaw actuator displacements, and axial position of the output coupler), with over 500,000 paired samples for data‐driven alignment. Given a pair of beam profiler images exhibiting distinct beam patterns under different configurations, the system predicts the control-parameter changes required to realign the resonator. Leveraging this dataset, we propose a novel two-stage deep learning framework for automatic resonator alignment. In Stage 1, a multi-scale CNN augmented with cross-attention and correlation-difference modules, extracts features and outputs an initial coarse prediction of alignment parameters. In Stage 2, a feature-difference map is computed by subtracting the paired feature representations and fed into an iterative refinement module to correct residual misalignments. The final prediction combines coarse and refined estimates, integrating global context with fine-grained corrections for accurate inference. Experiments on our dataset and a different instance of the same physical system from which the CNN was trained suggest superior accuracy and practicality to manual alignment.