Tsinghua University, Beijing, People's Republic of China.
IEEE Trans Vis Comput Graph. 2010 May-Jun;16(3):407-18. doi: 10.1109/TVCG.2009.88.
This paper presents a robust multiview stereo (MVS) algorithm for free-viewpoint video. Our MVS scheme is totally point-cloud-based and consists of three stages: point cloud extraction, merging, and meshing. To guarantee reconstruction accuracy, point clouds are first extracted according to a stereo matching metric which is robust to noise, occlusion, and lack of texture. Visual hull information, frontier points, and implicit points are then detected and fused with point fidelity information in the merging and meshing steps. All aspects of our method are designed to counteract potential challenges in MVS data sets for accurate and complete model reconstruction. Experimental results demonstrate that our technique produces the most competitive performance among current algorithms under sparse viewpoint setups according to both static and motion MVS data sets.
本文提出了一种用于自由视点视频的鲁棒多视点立体（MVS）算法。我们的 MVS 方案完全基于点云，由三个阶段组成：点云提取、合并和网格处理。为了保证重建精度，首先根据对噪声、遮挡和纹理不足具有鲁棒性的立体匹配度量标准提取点云。然后，在合并和网格处理步骤中，检测并融合视觉外壳信息、边界点和隐式点，并融合点保真度信息。我们方法的各个方面都旨在应对 MVS 数据集在准确和完整模型重建方面的潜在挑战。实验结果表明，根据静态和动态 MVS 数据集，我们的技术在稀疏视点设置下产生了比当前算法最具竞争力的性能。
