Real-Time Rendering Based on GPU for Binocular Stereo System

In binocular real-time stereo system based on depth, how to accurately and quickly fill big holes generated by DIBR is a key problem. This paper presents a real-time rendering algorithm based on GPU. Hole mask image is rendered in order to get the corresponding texture information for big holes at the sending, which can be used to fill the big holes at the receiving. Small holes are filled by linear interpolation algorithm. The experiments show that the proposed method achieves better hole filling effect. In order to meet the real-time requirement, GPU acceleration is applied in this paper. Firstly, per-pixels are projected to 3D space using CUDA, Secondly, these pixels are inversely projected to 2D plane using Open GL. Running on NVIDIA Quadro 600 GPU, with the resolution of 1024 × 768 and 1920 × 1080, the proposed method reaches about 45fps and 28fps respectively, meanwhile achieves real-time and better quality.

[1]  Jong-Il Park,et al.  Fast view synthesis using GPU for 3D display , 2008, IEEE Transactions on Consumer Electronics.

[2]  Hideo Saito,et al.  A Novel Inpainting-Based Layered Depth Video for 3DTV , 2011, IEEE Transactions on Broadcasting.

[3]  Ken Chen,et al.  Asymmetric Coding of Multi-View Video Plus Depth Based 3-D Video for View Rendering , 2012, IEEE Transactions on Multimedia.

[4]  Dongxiao Li,et al.  Asymmetric bidirectional view synthesis for free viewpoint and three-dimensional video , 2009, IEEE Transactions on Consumer Electronics.

[5]  Pei-Jun Lee,et al.  Nongeometric Distortion Smoothing Approach for Depth Map Preprocessing , 2011, IEEE Transactions on Multimedia.

[6]  Zhang Ming,et al.  A New Virtual View Rendering Method Based on Depth Image , 2010, 2010 Asia-Pacific Conference on Wearable Computing Systems.

[7]  Hua Li,et al.  A new double-sided DIBR method for virtual view generation in 3DTV , 2011, 2011 IEEE 13th International Conference on Communication Technology.

[8]  Licheng Jiao,et al.  Depth-preserving DIBR based on disparity map over T-DMB , 2010 .

[9]  Zhen Wang,et al.  A novel approach for depth image based rendering, based on non-linear transformation of depth values , 2011, 2011 International Conference on Image Analysis and Signal Processing.