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 2004.04242cs.CVcs.GR
收藏

深流形先验

Deep Manifold Prior

University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校)

Matheus Gadelha, Rui Wang, Subhransu Maji

摘要:

我们提出了一个流形结构化数据的先验,如3D形状的表面,其中采用深度神经网络从随机初始化开始使用梯度下降重建目标形状。我们证明了以这种方式生成的表面是光滑的,具有高斯过程特征的极限行为,并且我们在数学上推导出了全连接和卷积网络的这些特性。我们证明了我们的方法在各种各样的流形重建应用,如点云去噪和插值,实现了相当好的结果对竞争力的基线,而不需要训练数据。我们还表明,当训练数据是可用的,我们的方法允许开发替代参数化的表面的框架下的masNet,导致一个紧凑的网络架构和更好的重建结果的标准图像形状重建基准。

英文摘要:

We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization. We show that surfaces generated this way are smooth, with limiting behavior characterized by Gaussian processes, and we mathematically derive such properties for fully-connected as well as convolutional networks. We demonstrate our method in a variety of manifold reconstruction applications, such as point cloud denoising and interpolation, achieving considerably better results against competitive baselines while requiring no training data. We also show that when training data is available, our method allows developing alternate parametrizations of surfaces under the framework of AtlasNet, leading to a compact network architecture and better reconstruction results on standard image to shape reconstruction benchmarks.

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。

↑