Diffracted waves contain a great deal of valuable information about small-scale subsurface structure such as faults, pinch-outs, karsts, and fractures, which are closely related to hydrocarbon accumulation and production. Therefore, diffraction separation and imaging with high spatial resolution play an increasingly critical role in seismic exploration. We have applied the geometric-mean reverse time migration (GmRTM) method to diffracted waves for imaging only subsurface diffractors based on the difference of the wave phenomena between diffracted and reflected waves. Numerical tests prove the advantages of this method on diffraction imaging with higher resolution as well as fewer artifacts compared to conventional RTM even when we only have a small number of receivers. Then, we developed a workflow to extract diffraction information using a fully data-driven method, called common-reflection surface (CRS), before we applied GmRTM. Application of this workflow indicates that GmRTM further improves the quality of the image by combining with the diffraction-separation technique CRS in the data domain.