arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.07967cs.CVcs.LG
收藏

内在神经场:流形上的学习函数

Intrinsic Neural Fields: Learning Functions on Manifolds

University of Siegen(锡根大学);Technical University of Munich(慕尼黑工业大学)

Lukas Koestler, Daniel Grittner, Michael Moeller, Daniel Cremers, Zorah Lähner

摘要:

神经领域由于其在新视图合成、几何重构和生成式建模方面的优异性能而在计算机视觉界获得了极大的关注。它们的一些优点是具有良好的理论基础,并且在当前的深度学习框架中易于实现。虽然神经场已被应用于流形上的信号,例如,对于纹理重建,它们的表示被限制为将形状外嵌到欧几里得空间中。外在嵌入忽略了已知的内在流形性质,是不灵活的。学习功能的转移。为了克服这些局限性,这项工作引入了内在的神经领域,一种新的和通用的表示流形上的神经领域。内禀神经场结合了神经场的优点和Laplace-Beltrami算子的谱性质。我们从理论上表明,内在的神经领域继承了许多理想的属性的外在神经领域的框架,但表现出额外的内在品质,如等距不变性。在实验中,我们证明了内在神经场可以从具有最先进质量的图像中重建高保真纹理,并且对底层流形的离散化具有鲁棒性。我们通过处理各种应用来展示内在神经场的多功能性:变形形状和不同形状之间的纹理传输,具有视图依赖性的真实图像的纹理重建,以及网格和点云上的离散化不可知学习。

英文摘要:

Neural fields have gained significant attention in the computer vision community due to their excellent performance in novel view synthesis, geometry reconstruction, and generative modeling. Some of their advantages are a sound theoretic foundation and an easy implementation in current deep learning frameworks. While neural fields have been applied to signals on manifolds, e.g., for texture reconstruction, their representation has been limited to extrinsically embedding the shape into Euclidean space. The extrinsic embedding ignores known intrinsic manifold properties and is inflexible wrt. transfer of the learned function. To overcome these limitations, this work introduces intrinsic neural fields, a novel and versatile representation for neural fields on manifolds. Intrinsic neural fields combine the advantages of neural fields with the spectral properties of the Laplace-Beltrami operator. We show theoretically that intrinsic neural fields inherit many desirable properties of the extrinsic neural field framework but exhibit additional intrinsic qualities, like isometry invariance. In experiments, we show intrinsic neural fields can reconstruct high-fidelity textures from images with state-of-the-art quality and are robust to the discretization of the underlying manifold. We demonstrate the versatility of intrinsic neural fields by tackling various applications: texture transfer between deformed shapes & different shapes, texture reconstruction from real-world images with view dependence, and discretization-agnostic learning on meshes and point clouds.

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。

↑