Visibility-Aware Pixelwise View Selection for Multi-View Stereo Matching

TL;DR

This paper introduces a visibility-aware pixelwise view selection method for multi-view stereo that refines view choices based on visibility, improving detail recovery in occluded and low-texture areas.

Contribution

It proposes a novel visibility-guided view selection scheme combined with an Artificial Multi-Bee Colony algorithm for enhanced multi-view stereo matching.

Findings

Achieves state-of-the-art results among non-learning methods on DTU dataset.

Better handles occlusions and low-texture regions.

Improves detail recovery in challenging areas.

Abstract

The performance of PatchMatch-based multi-view stereo algorithms depends heavily on the source views selected for computing matching costs. Instead of modeling the visibility of different views, most existing approaches handle occlusions in an ad-hoc manner. To address this issue, we propose a novel visibility-guided pixelwise view selection scheme in this paper. It progressively refines the set of source views to be used for each pixel in the reference view based on visibility information provided by already validated solutions. In addition, the Artificial Multi-Bee Colony (AMBC) algorithm is employed to search for optimal solutions for different pixels in parallel. Inter-colony communication is performed both within the same image and among different images. Fitness rewards are added to validated and propagated solutions, effectively enforcing the smoothness of neighboring pixels and allowing better handling of textureless areas. Experimental results on the DTU dataset show our method achieves state-of-the-art performance among non-learning-based methods and retrieves more details in occluded and low-textured regions.