LAUSR

Interferometric phase denoising is a vital procedure for interferometric synthetic aperture radar (InSAR)-based remote sensing techniques because it can improve the accuracy of the final InSAR product. Here, we propose a deep convolutional neural network (DCNN)-based InSAR phase denoising method, abbreviated PDNet. Given an ideal wrapped phase, $\bar {\varphi }$ , the PDNet learns the self-similarity function (SSF) of $\bar {\varphi }$ from the input interferogram. After training, the PDNet obtains filtered wrapped phases using the maximum-likelihood approach by exhausting all $\bar {\varphi }\text{s}$ from $-\pi $ to $\pi $ . Unlike a boxcar-based filtering method, the PDNet does not consist of an “averaging operation” on the spatial domain, and the resolution loss and interferometric fringe distortion will not directly affect the PDNet result. Thus, PDNet can be considered a nonlocal (NL) phase denoising approach. Analyses and results show that PDNet is an almost near-real-time denoising algorithm. Its denoising accuracy is higher than that of the available model- and learning-based InSAR phase denoising methods.