Visibility-Aware Pixelwise View Selection for Multi-View Stereo Matching
The performance of PatchMatch-based multi-view stereo algorithms is greatly influenced by the choice of source views used for matching cost computation. Existing methods usually detect occlusions in a rather ad-hoc way, which can negatively impact the computation. In contrast, this thesis introduces an innovative approach that deliberately models view visibility. We present a novel visibility-guided pixelwise view selection scheme that progressively refines the set of source views for each pixel in the reference view using visibility information from validated solutions. Furthermore, the Artificial Multi-Bee Colony (AMBC) algorithm is leveraged to parallelly search optimal solutions for different pixels. To ensure the smoothness of neighboring pixels and better handling textureless areas, rewards are assigned to solutions that come from validated sources. Our method, validated through experiments on two datasets, improves the recovery of details in occluded and low-textured regions, demonstrating state-of-the-art performance on demanding scenes.