Multi-View Azimuth Stereo via Tangent Space Consistency
Multi-View Azimuth Stereo via Tangent Space Consistency
复制标题
DOI：
10.1109/cvpr52729.2023.00086
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Xu Cao;Hiroaki Santo;Fumio Okura;Y. Matsushita
中科院分区：
文献类型：
--
作者：
Xu Cao;Hiroaki Santo;Fumio Okura;Y. Matsushita
提出了一种仅利用标定后的多视点表面方位图进行三维重建的方法。本文提出的多视点方位角立体方法，对于传统的多视点立体方法难以处理的无纹理或镜面，是一种有效的方法。我们引入了切线空间一致性的概念：一个曲面点的多视角方位观测应该提升到相同的切线空间。利用这种一致性，我们通过优化神经隐式曲面表示来恢复形状。我们的方法利用了光度立体方法或偏振成像的稳健方位角估计能力，同时绕过了潜在的复杂的天顶角估计。利用不同来源的方位图进行的实验验证了我们的方法在没有天顶角的情况下也能准确地恢复形状。
We present a method for 3D reconstruction only using calibrated multi-view surface azimuth maps. Our method, multi-view azimuth stereo, is effective for textureless or specular surfaces, which are difficult for conventional multi-view stereo methods. We introduce the concept of tangent space consistency: Multi-view azimuth observations of a surface point should be lifted to the same tangent space. Leveraging this consistency, we recover the shape by optimizing a neural implicit surface representation. Our method harnesses the robust azimuth estimation capabilities of photometric stereo methods or polarization imaging while bypassing potentially complex zenith angle estimation. Experiments using azimuth maps from various sources validate the accurate shape recovery with our method, even without zenith angles.