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 2401.01391cs.CVcs.GRcs.LG
收藏

关于使用配备位置编码的MLP学习SDF的最优采样

On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding

University of Hong Kong(香港大学);University of British Columbia(不列颠哥伦比亚大学);City University of Hong Kong(香港城市大学);Zhejiang University(浙江大学);Texas A&M University(德克萨斯农工大学)

Guying Lin, Lei Yang, Yuan Liu, Congyi Zhang, Junhui Hou, Xiaogang Jin, Taku Komura, John Keyser, Wenping Wang

AI总结:

本文通过傅里叶分析提出一种估计配备位置编码的MLP固有频率的方法,并基于奈奎斯特-香农采样定理确定最优训练采样率,有效消除SDF学习中的噪声伪影并提升拟合性能。

摘要:

神经隐式场,例如形状的神经符号距离场(SDF),已成为许多应用(如编码3D形状和执行碰撞检测)的强大表示。通常,隐式场由配备位置编码(PE)的多层感知机(MLP)编码,以捕捉高频几何细节。然而,这种配备PE的MLP的一个显著副作用是学习到的隐式场中存在噪声伪影。虽然提高采样率通常可以缓解这些伪影,但在本文中,我们旨在通过傅里叶分析的视角解释这一不良现象。我们设计了一种工具来确定适当的采样率,以学习准确的神经隐式场且无不理想的副作用。具体而言,我们提出了一种简单而有效的方法,基于网络响应的傅里叶分析来估计具有随机权重的给定网络的固有频率。观察到配备PE的MLP的固有频率远高于PE层中的最高频率分量。遵循奈奎斯特-香农采样定理针对该固有频率进行采样,使我们能够确定适当的训练采样率。我们在SDF拟合的设置中实证表明,该推荐采样率足以确保准确的拟合结果,而进一步提高采样率不会进一步显著降低拟合误差。仅使用我们的采样策略训练配备PE的MLP,即可获得优于现有方法的性能。

英文摘要:

Neural implicit fields, such as the neural signed distance field (SDF) of a shape, have emerged as a powerful representation for many applications, e.g., encoding a 3D shape and performing collision detection. Typically, implicit fields are encoded by Multi-layer Perceptrons (MLP) with positional encoding (PE) to capture high-frequency geometric details. However, a notable side effect of such PE-equipped MLPs is the noisy artifacts present in the learned implicit fields. While increasing the sampling rate could in general mitigate these artifacts, in this paper we aim to explain this adverse phenomenon through the lens of Fourier analysis. We devise a tool to determine the appropriate sampling rate for learning an accurate neural implicit field without undesirable side effects. Specifically, we propose a simple yet effective method to estimate the intrinsic frequency of a given network with randomized weights based on the Fourier analysis of the network's responses. It is observed that a PE-equipped MLP has an intrinsic frequency much higher than the highest frequency component in the PE layer. Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate. We empirically show in the setting of SDF fitting that this recommended sampling rate is sufficient to secure accurate fitting results, while further increasing the sampling rate would not further noticeably reduce the fitting error. Training PE-equipped MLPs simply with our sampling strategy leads to performances superior to the existing 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。

↑