Combining multi-view stereo and super resolution in a unified framework

In multi-view stereo setting, pixel correspondence problem and super resolution problem are inter-related in a sense that the result of each problem could help to solve the other. In this paper, we propose a novel method to solve two problems together by optimizing a unified energy functional. Main difference from the previous works is that the consistency between high resolution images is considered along with consideration to the consistency of high-resolution and low-resolution image pair with the same viewpoint. Experimental results show that our method outperforms the naive combination of single image super resolution and multi-view stereo method.