In the field of visual processing, the three-dimensional (3D) video signal processing has become a hot trend and also received considerable attention. The 3D displays enhance visual quality more than two-dimensional (2D) displays do. But the lack of 3D content is becoming an important factor that limits its development. Also at this stage, the depth information required for 3D displays is unavailable in the conventional 2D content. Therefore, 2D into 3D image conversion has become an important issue in emerging 3D applications. Here a novel algorithm that automatically converts 2D images into 3D ones. The proposed algorithm first segments the image into object groups by choosing an effective grouping method. This is done with the help of the edge information. A depth map is then assigned based on a hypothesized depth gradient model. Next, the depth map is then assigned by cooperating with a cross bilateral filter. This is very much essential to generate visually comfortable depth maps efficiently and also to diminish the blocky artifacts. Then the filtered image is processed using a depth image based rendering method. Thus the final 3D image with the left and right view can be readily generated from the input 2D image.