The traditional synthetic aperture radar (SAR) imaging algorithm typically demands substantial computational resources due to its involvement in large-scale matrix operations, which presents challenges for imaging in expansive scenes. By leveraging the reversibility of the imaging process, a method that simulates the inverse process of generating echoes can be employed to expedite imaging. This approach shares the computational complexity of the matched filter algorithm, thereby enabling imaging of large scenes. However, the iteration-based algorithm necessitates manual parameter adjustments, which can be somewhat arbitrary and challenging to optimize effectively. Consequently, employing neural networks to train these parameters not only enhances imaging speed but also enhances imaging quality. Moreover, the Self-supervised Azimuth Ambiguity Suppression Network (SAAS-Net) introduced in this study effectively achieves azimuth ambiguity suppression without necessitating alterations to the hardware architecture. The experiments indicate that the algorithm proposed in this paper can achieve rapid imaging while maintaining computational accuracy consistent with matched filter algorithms such as chirp-scaling algorithm.