Point cloud-based railway track surface extraction is a crucial technology for railway inspection. It is still challenging to extract railway track surfaces from point cloud data due to the variable quantities, densities, and diverse scenarios, which limit the applicability and versatility of existing methods. To address these limitations, we propose a bidirectional cloth simulation approach that utilizes the geometric structural characteristics of the track surface for rapid extraction. This method applies simulated cloth in both bottom-up and top-down directions to the roadbed. Our method can process hundreds of thousands of point clouds per second and is adaptable to various point cloud types (TLS and MLS), roadbed types (ballasted and ballast-less), rail types (single, double and turnouts). It achieves a completeness of over 97 % in the automatic extraction of both ballasted single and ballast-less double tracks and a correctness of over 89 % in the extraction of complex turnouts.