PhySR：用于射电合成成像超分辨率重建的物理信息神经网络
PhySR: Physics-Informed Neural Network for Super-Resolution Reconstruction in Radio Synthesis Imaging
浏览论文内容
中文总结 AI 辅助
PhySR是一种结合物理前向模型的端到端物理信息神经网络，用于射电合成成像超分辨率重建，在模拟SKA-Mid数据上的表现优于现有通用方法和主流深度学习模型，且在多倍率超分辨率任务中保持稳定。
中文摘要 AI 辅助
射电望远镜阵列受天线数量和基线分布限制，导致空间频率采样不完整，图像分辨率有限，且受主波束与合成波束耦合影响出现模糊、畸变及小尺度结构损失。现有通用模型驱动方法依次消除观测效应，可能累积误差，无法直接解决成像分辨率有限的问题；数据驱动方法则缺乏显式物理约束。我们提出PhySR，一种端到端的物理信息神经网络，结合U-Net骨干网络、动态级联上采样、多尺度特征残差模块，以及包含主波束响应、PSF卷积和尺度映射的可微分物理前向模型。PhySR无需高分辨率标签，直接从低分辨率脏图像重建高分辨率图像，同时保持观测域一致性。对模拟SKA-Mid数据的实验显示，在4倍超分辨率任务中，PhySR达到44.65 dB的PSNR、0.9940的SSIM和0.0065的RMSE；与现有通用方法相比，PSNR和SSIM分别提升约13.23 dB和0.3760；与主流深度学习模型相比，PSNR和SSIM分别提升6.50 dB和0.0682，RMSE降低0.0069。PhySR在2倍和8倍超分辨率任务中也保持稳定，且观测域一致性误差较低，在耦合效应消除、小尺度结构恢复和物理一致性方面展现出优势。
英文摘要
Radio telescope arrays are constrained by the number of antennas and baseline distribution, resulting in incomplete spatial-frequency sampling, limited image resolution, and blurring, distortion, and loss of small-scale structures caused by coupling between the primary and synthesized beams. Existing general-purpose model-driven methods remove observational effects sequentially and may accumulate errors, but cannot directly address limited imaging resolution, while data-driven methods lack explicit physical constraints. We propose PhySR, an end-to-end physics-informed neural network that combines a U-Net backbone, dynamic cascaded upsampling, a multiscale feature residual module, and a differentiable physical forward model incorporating the primary beam response, PSF convolution, and scale mapping. PhySR directly reconstructs high-resolution images from low-resolution dirty images without high-resolution labels while maintaining observation-domain consistency. Experiments on simulated SKA-Mid data show that, for 4x super-resolution, PhySR achieves a PSNR of 44.65 dB, an SSIM of 0.9940, and an RMSE of 0.0065. Compared with existing general-purpose methods, PSNR and SSIM improve by approximately 13.23 dB and 0.3760, respectively. Compared with mainstream deep learning models, PSNR and SSIM improve by 6.50 dB and 0.0682, while RMSE decreases by 0.0069. PhySR also remains stable for 2x and 8x super-resolution and achieves low observation-domain consistency errors, demonstrating advantages in coupling-effect removal, small-scale structure recovery, and physical consistency.
