CRF‐based depth refinement with hybrid depth information
Qiuyan Tao, Lianghao Wang, Dongxiao Li, Ming Zhang · Electronics Letters · 2017
A conditional random field (CRF)‐based framework is proposed for depth refinement. It consists of two phases: depth impainting and depth super‐resolution (SR). The CRF inference procedure uses depth information enhanced in three different ways to ensure the accurate edge of the final depth output. The experimental results show the effectiveness of the method both numerically and visually. Note that the method produces depth map with better edge than other depth impainting and SR methods do.