Multi-Scale Geometric Consistency Guided Multi-View Stereo
This work addresses depth estimation challenges in computer vision, especially for low-textured regions, with incremental improvements over existing methods.
The paper tackles the problem of accurate and complete depth map estimation in multi-view stereo, particularly in low-textured areas, by proposing an efficient method that achieves state-of-the-art performance on extensive datasets.
In this paper, we propose an efficient multi-scale geometric consistency guided multi-view stereo method for accurate and complete depth map estimation. We first present our basic multi-view stereo method with Adaptive Checkerboard sampling and Multi-Hypothesis joint view selection (ACMH). It leverages structured region information to sample better candidate hypotheses for propagation and infer the aggregation view subset at each pixel. For the depth estimation of low-textured areas, we further propose to combine ACMH with multi-scale geometric consistency guidance (ACMM) to obtain the reliable depth estimates for low-textured areas at coarser scales and guarantee that they can be propagated to finer scales. To correct the erroneous estimates propagated from the coarser scales, we present a novel detail restorer. Experiments on extensive datasets show our method achieves state-of-the-art performance, recovering the depth estimation not only in low-textured areas but also in details.