Iterative Volume Fusion for Asymmetric Stereo Matching
This addresses a practical problem in 3D computer vision for applications using asymmetric cameras like tele-wide systems, representing an incremental improvement over existing stereo matching methods.
The paper tackles stereo matching in asymmetric multi-camera systems where visual properties differ between cameras, which disrupts traditional methods. It proposes an Iterative Volume Fusion network that achieves robust performance against significant visual asymmetry, as confirmed by experiments on benchmark datasets.
Stereo matching is vital in 3D computer vision, with most algorithms assuming symmetric visual properties between binocular visions. However, the rise of asymmetric multi-camera systems (e.g., tele-wide cameras) challenges this assumption and complicates stereo matching. Visual asymmetry disrupts stereo matching by affecting the crucial cost volume computation. To address this, we explore the matching cost distribution of two established cost volume construction methods in asymmetric stereo. We find that each cost volume experiences distinct information distortion, indicating that both should be comprehensively utilized to solve the issue. Based on this, we propose the two-phase Iterative Volume Fusion network for Asymmetric Stereo matching (IVF-AStereo). Initially, the aggregated concatenation volume refines the correlation volume. Subsequently, both volumes are fused to enhance fine details. Our method excels in asymmetric scenarios and shows robust performance against significant visual asymmetry. Extensive comparative experiments on benchmark datasets, along with ablation studies, confirm the effectiveness of our approach in asymmetric stereo with resolution and color degradation.