Inferring high resolution image from single low resolution (LR) input is ill-posed and deep learning helps to some extent. Latest algorithms take the advantage of the Generative Adversarial Network (GAN) and present photo-realistic results by learning low/high resolution mappings from super resolution datasets. However, training of GANs can be hard and traditional GAN-based architectures often exhibit noise and texture distortion in their super-resolution (SR) results. Proposes mask-aided adversarial training strategy for current GAN-based SR frameworks. During training, mask module helps the discriminator by introducing additional perceptual quality information with generator’s outputs and the ground truth images. We select three current state-of-the-art GAN-based SR models and integrate our mask module into their adversarial training. Mask-aided models yield better results in both quantitative and qualitative benchmarks than the original ones. Mask module only modifies GAN framework and thus suitable for many GAN-based solutions for further improving the SR perceptual quality.