A Real-Time Full HD 2D-to-3D Video Conversion System Based on FPGA

The 2D to 3D conversion technique plays an important role in the development and promotion of three-dimensional television (3DTV), because it can provide adequate supply of high-quality 3D program content. This Paper focuses on the real-time implementation of 2D-3D system, of which the major parts are source depth-map generation and depth image-based rendering (DIBR). The depth-map is generated by multi-depth cues, according to the types of the 2D scene, including luminance and color, visual saliency and adaptive depth models. Then the original 2D image or video is converted to stereoscopic one by DIBR with the depth map. The proposed system is accelerated by being designed in new hardware architecture on FPGA. Our method is verified on various sequences and experiment results show that, the system can achieve 30 frames per second for processing full HD (1920×1080) video on Xilinx Virtex IV XC4VSX25 while the resulting image or video is both realistic and visual pleasing.