Two-shot random phase-shifting interferometry has been actively investigated and improved owing to more de-manding requirements in investigating dynamic phenomena or sensing some transient events. Given the back-ground intensity and phase step knowledge, a reconstruction algorithm can be used to recover a complex-valued signal from intensity-only measurements. Most algorithms assume the background intensity and modulation am-plitude in a frame of interferogram are constant variables; however, in realistic systems, they vary laterally and axially across the field of view. The model can be used but often appears less precise. In this work, we propose an approach that leverages the iterative method to cope with spatially varying background intensity and modu-lation amplitude. Our approach, termed the two-frame advanced iterative self-tuning algorithm, uses the spatial mean algorithm paired with an iterative procedure to search the phase step from two captured fringe patterns. It represents a novel approach to reliable and practical two-step phase-shifting interferometry without pre-filtering due to the cancelation of simultaneously obtaining the phase shifts and measured phase through iterative oper-ation in the spatial-temporal domain. Experimental results obtained using the proposed method indicate that it is a simple and robust solution for phase extraction from a two-frame unknown phase shift fringe pattern with spatially varying background intensity and modulation amplitude.