当前位置: X-MOL 学术arXiv.cs.RO › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator
arXiv - CS - Robotics Pub Date : 2020-05-17 , DOI: arxiv-2005.08165
Rui Fan, Hengli Wang, Bohuan Xue, Huaiyang Huang, Yuan Wang, Ming Liu, Ioannis Pitas

Over the past decade, significant efforts have been made to improve the trade-off between speed and accuracy of surface normal estimators (SNEs). This paper introduces an accurate and ultrafast SNE for structured range data. The proposed approach computes surface normals by simply performing three filtering operations, namely, 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 the method, no similar method already exists in the literature. In our experiments, we created three large-scale synthetic datasets (easy, medium and hard) using 24 3-dimensional (3D) mesh models. Each mesh model is used to generate 1800--2500 pairs of 480x640 pixel depth images and the corresponding surface normal ground truth from different views. The average angular errors with respect to the easy, medium and hard datasets are 1.6 degrees, 5.6 degrees and 15.3 degrees, respectively. Our C++ and CUDA implementations achieve a processing speed of over 260 Hz and 21 kHz, respectively. Our proposed SNE achieves a better overall performance than all other existing computer vision-based SNEs. Our datasets and source code are publicly available at: sites.google.com/view/3f2n.

中文翻译:

三滤波器到法线:一种准确且超快的表面法线估计器

在过去的十年中,已经做出了重大努力来改善表面法线估计器 (SNE) 的速度和准确性之间的权衡。本文介绍了一种用于结构化范围数据的准确且超快的 SNE。所提出的方法通过在逆深度图像或视差图像上简单地执行三个滤波操作来计算表面法线,即两个图像梯度滤波器(分别在水平和垂直方向上)和一个均值/中值滤波器。尽管该方法很简单,但文献中还没有类似的方法。在我们的实验中,我们使用 24 个 3D (3D) 网格模型创建了三个大型合成数据集(简单、中等和困难)。每个网格模型用于从不同视图生成 1800--2500 对 480x640 像素深度图像和相应的表面法线地面实况。简单、中等和困难数据集的平均角度误差分别为 1.6 度、5.6 度和 15.3 度。我们的 C++ 和 CUDA 实现分别实现了超过 260 Hz 和 21 kHz 的处理速度。我们提出的 SNE 比所有其他现有的基于计算机视觉的 SNE 实现了更好的整体性能。我们的数据集和源代码可在以下网址公开获取:sites.google.com/view/3f2n。我们提出的 SNE 比所有其他现有的基于计算机视觉的 SNE 实现了更好的整体性能。我们的数据集和源代码可在以下网址公开获取:sites.google.com/view/3f2n。我们提出的 SNE 比所有其他现有的基于计算机视觉的 SNE 实现了更好的整体性能。我们的数据集和源代码可在以下网址公开获取:sites.google.com/view/3f2n。
更新日期:2020-05-26
down
wechat
bug