Learning Transformation Synchronization
Learning Transformation Synchronization
复制标题
DOI：
10.1109/cvpr.2019.00827
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Xiangru Huang;Zhenxiao Liang;Xiaowei Zhou;Yao Xie;L. Guibas;Qi-Xing Huang
中科院分区：
文献类型：
--
作者：
Xiangru Huang;Zhenxiao Liang;Xiaowei Zhou;Yao Xie;L. Guibas;Qi-Xing Huang
重建物理对象的3D模型通常需要我们将从不同相机姿势获得的深度扫描对准到相同的坐标系中。这种全局对齐问题的解决方案通常分两个步骤进行。第一步是使用现成的技术估计成对扫描之间的相对转换。由于在扫描对之间呈现的信息有限，所产生的相对变换通常是有噪声的。然后，第二步联合优化所有输入深度扫描之间的相对变换。这一步中使用的一个自然约束是循环一致性约束，它允许我们通过检测不一致的循环来删除不正确的相对转换。然而，这些方法的性能在很大程度上依赖于输入相对转换的质量。我们建议使用神经网络来学习与每个相对变换相关联的权重，而不是仅仅使用相对变换作为输入来执行变换同步。我们的方法在使用加权相对变换的变换同步和使用神经网络预测输入相对变换的新权重之间交替。我们在广泛的数据集上展示了这种方法的有效性。
Reconstructing the 3D model of a physical object typically requires us to align the depth scans obtained from different camera poses into the same coordinate system. Solutions to this global alignment problem usually proceed in two steps. The first step estimates relative transformations between pairs of scans using an off-the-shelf technique. Due to limited information presented between pairs of scans, the resulting relative transformations are generally noisy. The second step then jointly optimizes the relative transformations among all input depth scans. A natural constraint used in this step is the cycle-consistency constraint, which allows us to prune incorrect relative transformations by detecting inconsistent cycles. The performance of such approaches, however, heavily relies on the quality of the input relative transformations. Instead of merely using the relative transformations as the input to perform transformation synchronization, we propose to use a neural network to learn the weights associated with each relative transformation. Our approach alternates between transformation synchronization using weighted relative transformations and predicting new weights of the input relative transformations using a neural network. We demonstrate the usefulness of this approach across a wide range of datasets.