Coronary artery disease (CAD) is the leading cause of death worldwide. The most widely used and precise method for diagnosing CAD is invasive coronary angiography (ICA). Fractional flow reserve (FFR) is an index of the functional severity of coronary stenoses that requires additional invasive intervention during ICA. With advancements in artificial intelligence (AI) technology, the estimation of FFR using AI is gaining popularity to meet the need for fast, accurate, and less invasive FFR estimation that can integrate into physicians' workflows. This review presents the current progress in this area by analyzing studies employing various approaches.