Gipuma: Massively Parallel Multi-view Stereo Reconstruction
Gipuma: Massively Parallel Multi-view Stereo Reconstruction
复制标题
Gipuma：大规模并行多视图立体重建
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
K. Schindler
中科院分区：
文献类型：
--
作者：
S. Galliani;Katrin Lasinger;K. Schindler;K. Schindler
描述了苏黎世理工大学大地测量和摄影测量研究所开发的密集多视点匹配和三维点云重建方法。该方法通过在图形处理单元(GPU)上进行大规模并行处理，非常高效地从定向图像生成高质量的点云。它以开放源代码的形式提供。从技术上讲，该方法是PatchMatch Stereo算法的扩展：3D深度值和曲面法线向量在图像中迭代传播并进行细化，以找到每个视图的最大照片一致性深度图和法线场。照片一致性是在倾斜的切线平面上计算的，这样重建就不会受到正面平行偏差的影响。我们将PatchMatch扩展到3D场景空间，使得照片一致性可以在多个视图上聚合，从而允许更健壮和更准确的深度估计。此外，序列传播被局部的类似扩散的方案所取代，使得计算可以大规模并行化。所有计算都是局部的，因此计算时间与图像大小成线性关系，与并行线程的数量成反比。此外，内存要求也不高，因为每个像素只需要存储四个值。在基准数据集上的实验表明，我们的方法在一系列应用中提供了高精度和完备性的点云(分别为曲面)。
: We describe a method for dense multi-view matching and 3D point cloud reconstruction, which has been developed at the Institute of Geodesy and Photogrammetry of ETH Zurich. The method generates high-quality point clouds from oriented images very efficiently, by massively parallel processing on graphics processing units (GPUs). It is available as open-source code. Technically, the method is an extension of the PatchMatch Stereo algorithm: 3D depth values and surface normal vectors are iteratively propagated across the image and refined, in order to find a maximally photo-consistent depth map and normal field for each view. Photo-consistency is computed in a slanted tangent plane, such that the reconstruction does not suffer from fronto-parallel bias. We extend PatchMatch to 3D scene space, such that photo-consistency can be aggregated over multiple views, which allows for more robust and more accurate depth estimation. Moreover, the sequential propagation is replaced by a local, diffusion-like scheme, such that the computation can be massively parallelised. All computations are local, thus computation time is linear in the image size and inversely proportional to the number of parallel threads. Moreover, memory requirements are also modest, since only four values per pixel must be stored. Experiments on benchmark datasets show that our method delivers point clouds (respectively, surfaces) with high accuracy and completeness, across a range of applications.