An MRF-Based Depth Upsampling: Upsample the Depth Map With Its Own Property
Wei Liu, Shaoyong Jia, Penglin Li, Xiaogang Chen, Jie Yang, Qiang Wu · IEEE Signal Processing Letters · 2015
In this letter, we propose a novel method for upsampling the noisy low resolution depth map with the guidance of the companion color image. The problem is modeled with an Markov Random Field (MRF)-based optimization framework. The novelty relies on the smoothness term that is modeled with an exponential function as the error norm. By using this novel error norm, our method can take the property of the depth map into account. Depth discontinuity cues are not only obtained from the color image but also the depth map itself. Our method has much better performance in preserving sharp depth discontinuities and suppressing the texture copy artifacts. Experimental results show that our method outperforms state-of-art solutions in both visual quality and accuracy.