Abstract: Asymmetry in the pulse response will be introduced in the reconstruction of circular synthetic aperture sonar (CSAS) images using the time-domain back-projection algorithm, leading to reduced imaging resolution away from the imaging scene center. Theoretically, image blur caused by this asymmetry can be corrected by deconvolution with the point spread function (PSF) of the imaging system. However, the spatial variance in the PSF of CSAS, coupled with the ill-posed nature of deconvolution as an inverse problem, and its sensitivity to noise, results in poor correction of image blur. To address the spatial variance in the PSF, this paper utilizes Implicit Neural Representation (INR) neural networks for deconvolution of underwater CSAS images. This approach effectively corrects high-order phase errors in reconstructed images and enhances the algorithm's robustness through improvements in the INR network. Computer simulations and experiments on a lake demonstrate that this method outperforms traditional deconvolution methods, showcasing superior image enhancement capabilities.