SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo

Different from most state-of-the-art~(SOTA) algorithms that use static and uniform sampling methods with a lot of hypothesis planes to get fine depth sampling. In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range, which not only greatly reduce the number of planes but also finer sampling, for achieving the purpose of reducing computational and improving accuracy, named Non-Uniform Cost Volume. We present the SuperMVS network to implement Multi-View Stereo with Non-Uniform Cost Volume. SuperMVS is a coarse-to-fine framework with four stages. It can output a higher resolution and higher accurate depth map. Our SuperMVS achieved the SOTA results with low memory, low runtime, and fewer planes on the DTU datasets and Tanks \& Temples dataset.