Abstract: Depth of Field is an important factor to synthesize realistic photography effects. In our paper, we discuss a new image-based approach that can synthesize DoF effects without user iterations. Our approach can produce the based saliency maps with realtime performance. In particular, there is not depth information needed to capture from cameras. The depth information is approximated by using saliency maps. In particular, we take advantages of the flash non-flash image pairs to refine the DoF synthesis quality. The focused regions can be segmented using GrabCut. The experimental results show that the our image based DoF synthesis can simulate high-quality DoF effects efficiently.