Image Details

Choose export citation format:

Real-time Closed-loop Correction for Dynamic Wavefront Aberrations Using Deep Learning–based Focal-plane Wavefront Sensing

  • Authors: Lingxiao Zhang, Nanfei Yan, Libo Zhong, Qianhan Zhou, Youming Guo, Lanqiang Zhang, Changhui Rao

Lingxiao Zhang et al 2026 The Astrophysical Journal Supplement Series 287 .

  • Provider: AAS Journals

Caption: Figure 1.

(a) Schematic diagram of SFWC determining the correction direction through bidirectional perturbation feedback. (1) SF-CBAM-RN estimates a pair of inverted complex conjugate wavefronts from the aberrated focal-plane image. (2) The DM applies a pair of inverted complex conjugate wavefront correction amounts to obtain feedback images. (3) The final correction direction is determined based on the image quality of the bidirectional perturbation feedback images. (b) The closed-loop process with the adaptive filter: (1) construct the initial adaptive filter using the wavefront direction from the first few frames determined by the SFWC algorithm, and predict the wavefront direction of the current frame; (2) perform wavefront correction based on the predicted direction from the adaptive filter, combined with the estimation results from the ND-estimation SF-CBAM-RN model, using a single measurement; (3) evaluate the SR value of the focal-plane image obtained from this correction, provide feedback, and update the filter sequence.

Other Images in This Article

Show More

Copyright and Terms & Conditions

Additional terms of reuse