Abstract: In recent years, with the growing demand for public safety and the rapid development of intelligent surveillance networks, person re-identification (Re-ID) has become one of the hottest research topics in the field of computer vision, which aims at retrieving a person of interest through multiple cameras with non-overlapping views. First, the current classical person Re-ID datasets are introduced. Second, the latest GAN-based person Re-ID methods are focused on sorting out. These methods are classified into three categories: image-image style transfer, data enhancement and invariant feature learning according to the characteristics and application scenarios of GAN. And basic principles, advantages, and disadvantages are summarized for each category. Then, the states of the art of the classic algorithms mentioned are compared on the mainstream datasets. Finally, the present challeng-ing problems of person Re-ID and directions for future research are discussed.