Shading-based refinement on volumetric signed distance functions
Shading-based refinement on volumetric signed distance functions
复制标题
DOI：
10.1145/2766887
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
M. Zollhöfer;Angela Dai;Matthias Innmann;Chenglei Wu;M. Stamminger;C. Theobalt;M. Nießner
中科院分区：
文献类型：
--
作者：
M. Zollhöfer;Angela Dai;Matthias Innmann;Chenglei Wu;M. Stamminger;C. Theobalt;M. Nießner
我们提出了一种新的方法来获得精细尺度的细节，在3D重建生成的低预算RGB-D相机或其他商品扫描设备。由于这些传感器的深度数据是有噪声的，因此通常使用截断的带符号距离场来正则化噪声，这不幸地导致过度平滑的结果。在我们的方法中，我们利用RGB数据通过阴影线索来优化这些重建，因为颜色输入通常比深度数据具有更高的分辨率。因此，我们获得了具有高几何细节的重建，远远超出了相机本身的深度分辨率。我们的核心贡献是直接在隐式表面表示上进行基于阴影的细化，该表面表示是从全局对齐的RGB-D图像生成的。我们制定的体积距离场的逆阴影问题，并提出了一种新的目标函数，共同优化精细尺度的表面几何形状和空间变化的表面反射率。为了使亚毫米细节的有效重建，我们存储和处理我们的表面使用稀疏体素散列方案，我们通过引入网格层次结构来增强。量身定制的基于GPU的高斯-牛顿求解器使我们能够在几秒钟内将大型形状模型优化到以前看不到的分辨率。
We present a novel method to obtain fine-scale detail in 3D reconstructions generated with low-budget RGB-D cameras or other commodity scanning devices. As the depth data of these sensors is noisy, truncated signed distance fields are typically used to regularize out the noise, which unfortunately leads to over-smoothed results. In our approach, we leverage RGB data to refine these reconstructions through shading cues, as color input is typically of much higher resolution than the depth data. As a result, we obtain reconstructions with high geometric detail, far beyond the depth resolution of the camera itself. Our core contribution is shading-based refinement directly on the implicit surface representation, which is generated from globally-aligned RGB-D images. We formulate the inverse shading problem on the volumetric distance field, and present a novel objective function which jointly optimizes for fine-scale surface geometry and spatially-varying surface reflectance. In order to enable the efficient reconstruction of sub-millimeter detail, we store and process our surface using a sparse voxel hashing scheme which we augment by introducing a grid hierarchy. A tailored GPU-based Gauss-Newton solver enables us to refine large shape models to previously unseen resolution within only a few seconds.