arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.15484cs.LGcs.NE
收藏

使内隐神经表征本身规则化

Regularize implicit neural representation by itself

National University of Defense Technology(国防科技大学);Xi’an Jiaotong University(西安交通大学);Macau University of Science and Technology(澳门科技大学)

Zhemin Li, Hongxia Wang, Deyu Meng

摘要:

为了提高隐神经表征的泛化能力,提出了一种称为隐神经表征正则化器(INRR)的正则化器。INR是一个完全连接的网络,可以表示细节不受网格分辨率限制的信号。然而,它的泛化能力可以提高,特别是非均匀采样数据。所提出的INRR基于学习的狄利克雷能量(DE),其测量矩阵的行/列之间的相似性。拉普拉斯矩阵的平滑性通过用微小的INR参数化DE来进一步集成。INRR通过将信号的自相似性与拉普拉斯矩阵的平滑性完美地结合起来,提高了INR在信号表示中的通用性。通过精心设计的数值实验,揭示了INRR的一系列性质,包括动量方法,如收敛轨迹和多尺度相似性。此外,该方法可以改善其他信号表示方法的性能。

英文摘要:

This paper proposes a regularizer called Implicit Neural Representation Regularizer (INRR) to improve the generalization ability of the Implicit Neural Representation (INR). The INR is a fully connected network that can represent signals with details not restricted by grid resolution. However, its generalization ability could be improved, especially with non-uniformly sampled data. The proposed INRR is based on learned Dirichlet Energy (DE) that measures similarities between rows/columns of the matrix. The smoothness of the Laplacian matrix is further integrated by parameterizing DE with a tiny INR. INRR improves the generalization of INR in signal representation by perfectly integrating the signal's self-similarity with the smoothness of the Laplacian matrix. Through well-designed numerical experiments, the paper also reveals a series of properties derived from INRR, including momentum methods like convergence trajectory and multi-scale similarity. Moreover, the proposed method could improve the performance of other signal representation methods.

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。

↑