In this paper, an adaptive threshold-based gait authentication model is proposed, which incorporates the quality measure in the distance domain and maps them into the gradient domain to realize the optimal threshold of each gait sample, in contrast to the fixed threshold, as most of the authentication model utilizes. For accessing the quality measure of each gait, a gait covariate invariant generative adversarial network (GCI-GAN) is proposed to generate normal gait (canonical condition) irrespective of covariates (carrying, and viewing conditions) while preserving the subject identity. In particular, GCI-GAN connects to gradient weighted class activation mapping (Grad-CAMs) to obtain an attention mask from the significant components of input features, employs blending operation to manipulate specific regions of the input, and finally, multiple losses are employed to constrain the quality of generated samples. We validate the approach on gait datasets of CASIA-B and OU-ISIR and show a substantial increase in authentication rate over other state-of-the-art techniques.