A GPU implementation of level set multiview stereo

Variational methods that evolve surfaces according to PDEs have been quite successful for solving the multiview stereo shape reconstruction problem since [1]. However just like every other algorithm that tackles this problem, their running time is quite high (from dozens of minutes to several hours). Fortunately graphics hardware has shown a great potential for speeding up many low-level computer vision tasks. In this paper, we present the analysis of the different bottlenecks of the original implementation of [2] and show how to efficently port it to GPUs using well-known CPCPU techniques. We finally present some results and discuss the improvements.