arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.09458cs.CVcs.LG
收藏

学习转换同步

Learning Transformation Synchronization

ZJU-SenseTime Joint Lab of 3D Vision(浙江大学-商汤科技三维视觉联合实验室);UT Austin(德克萨斯大学奥斯汀分校);Zhejiang University(浙江大学);Georgia Tech(佐治亚理工学院);Facebook AI Research(Facebook人工智能研究院);Stanford University(斯坦福大学)

Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, Qixing Huang

摘要:

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齐到相同的坐标系中。这个全局对齐问题的解决方案通常分为两个步骤。第一步使用现成的技术估计扫描对之间的相对变换。由于成对扫描之间呈现的信息有限,因此所得到的相对变换通常是有噪声的。然后,第二步骤联合优化所有输入深度扫描之间的相对变换。在这一步中使用的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修剪不正确的相对转换。然而,这种方法的性能在很大程度上依赖于输入相对变换的质量。我们提出使用一个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。我们的方法交替变换同步使用加权相对变换和预测新的权重的输入相对变换使用神经网络。我们证明了这种方法在广泛的数据集的有用性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑