We innovate in stereo vision by explicitly providing analytical 3D surface models as viewed by a cyclopean eye model that incorporate depth discontinuities and occlusions. This geometrical foundation combined with learned stereo features allows our system to benefit from the strengths of both approaches. We also invoke a prior monocular model of surfaces to fill in occlusion regions or texture-less regions where data matching is not sufficient. Our results already are on par with the state-of-the-art purely data-driven methods and are of much better visual quality, emphasizing the importance of the 3D geometrical model to capture critical visual information. Such qualitative improvements may find applicability in virtual reality, for a better human experience, as well as in robotics, for reducing critical errors. Our approach aims to demonstrate that understanding and modeling geometrical properties of 3D surfaces is beneficial to computer vision research.

翻译：我们通过显式提供分析性三维表面模型进行立体视觉创新，该模型基于独眼视觉模型构建，并整合了深度不连续性与遮挡效应。这一几何基础与学习到的立体特征相结合，使我们的系统能够同时受益于两种方法的优势。我们还引入先验的单目表面模型，以填补数据匹配不足的遮挡区域或无纹理区域。我们的结果已与当前最先进的纯数据驱动方法性能相当，且具有更优的视觉质量，凸显了三维几何模型在捕捉关键视觉信息方面的重要性。此类定性改进可应用于虚拟现实领域以提升人类体验，亦可用于机器人技术以减少关键误差。我们的方法旨在证明：理解和建模三维表面的几何特性对计算机视觉研究具有重要价值。