论文标题
三过滤器到正常：准确而超快的表面正常估计器
Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator
论文作者
论文摘要
本文提出了三滤波器到正常（3F2N），这是一种精确而超快的表面正常估计器（SNE），该估计量（SNE）是为结构化范围传感器数据设计的，例如深度/差异图像。 3F2N SNE通过简单地在逆深度图像或差异图像上执行三个过滤操作（分别在水平和垂直方向上的两个图像梯度过滤器和平均/中位过滤器）来计算表面正常。尽管3F2N SNE的简单性，但文献中尚无类似的方法。为了评估我们提出的SNE的性能，我们使用24个3D网格型号创建了三个大规模合成数据集（易于，中等和硬），每种模型都用于生成1800--2500对深度图像（分辨率：480x640像素）和来自不同视图的相应的接地表面正常映射。 3F2N SNE展示了最先进的性能，表现优于所有其他基于几何的SNE，其中相对于简单，中和硬数据集的平均角度误差分别为1.66度，5.69度和15.31度。此外，我们的C ++和CUDA实现分别达到了260 Hz和21 kHz的处理速度。我们的数据集和源代码可在sites.google.com/view/3f2n上公开可用。
This paper proposes three-filters-to-normal (3F2N), an accurate and ultrafast surface normal estimator (SNE), which is designed for structured range sensor data, e.g., depth/disparity images. 3F2N SNE computes surface normals by simply performing three filtering operations (two image gradient filters in horizontal and vertical directions, respectively, and a mean/median filter) on an inverse depth image or a disparity image. Despite the simplicity of 3F2N SNE, no similar method already exists in the literature. To evaluate the performance of our proposed SNE, we created three large-scale synthetic datasets (easy, medium and hard) using 24 3D mesh models, each of which is used to generate 1800--2500 pairs of depth images (resolution: 480X640 pixels) and the corresponding ground-truth surface normal maps from different views. 3F2N SNE demonstrates the state-of-the-art performance, outperforming all other existing geometry-based SNEs, where the average angular errors with respect to the easy, medium and hard datasets are 1.66 degrees, 5.69 degrees and 15.31 degrees, respectively. Furthermore, our C++ and CUDA implementations achieve a processing speed of over 260 Hz and 21 kHz, respectively. Our datasets and source code are publicly available at sites.google.com/view/3f2n.
