Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity
This addresses a reliability issue in 3D reconstruction for computer vision applications, offering an incremental improvement by replacing depth range dependency with disparity-based estimation.
The paper tackles the problem of existing learning-based multi-view stereo methods failing when depth ranges are large or unreliable by proposing DispMVS, a disparity-based method that infers depth from pixel movement between views. It achieves state-of-the-art results on DTUMVS and Tanks&Temple datasets with lower GPU memory usage.
Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable. To address this problem, we propose a disparity-based MVS method based on the epipolar disparity flow (E-flow), called DispMVS, which infers the depth information from the pixel movement between two views. The core of DispMVS is to construct a 2D cost volume on the image plane along the epipolar line between each pair (between the reference image and several source images) for pixel matching and fuse uncountable depths triangulated from each pair by multi-view geometry to ensure multi-view consistency. To be robust, DispMVS starts from a randomly initialized depth map and iteratively refines the depth map with the help of the coarse-to-fine strategy. Experiments on DTUMVS and Tanks\&Temple datasets show that DispMVS is not sensitive to the depth range and achieves state-of-the-art results with lower GPU memory.