Abstract: With the development of oil and gas exploration, conventional isotropic Kirchhoff integral migration algorithm can no longer meet the requirements of high-precision imaging in complex structural areas. As a result, tilted transversely isotropic (TTI) media Kirchhoff integral migration has been widely adopted in industrial applications. To address the issues of low accuracy and computational inefficiency in traditional TTI media travel-time calculations, a travel-time computation method for TTI media based on Physics-Informed Neural Networks (PINN) is introduced into the Kirchhoff integral migration framework, enabling high-precision migration imaging in TTI media. Both model experiments and field data processing demonstrate that, compared to conventional finite-difference algorithms, the PINN-based approach significantly improves both the accuracy and efficiency of travel-time calculations, thereby enabling high quality TTI media Kirchhoff integral migration imaging.