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 2502.05482cs.CV
收藏

面向隐式神经表示的傅里叶特征嵌入鲁棒化

Robustifying Fourier Features Embeddings for Implicit Neural Representations

The University of Tokyo(东京大学)

Mingze Ma, Qingtian Zhu, Yifan Zhan, Zhengwei Yin, Hongjun Wang, Yinqiang Zheng

AI总结:

本文针对隐式神经表示中傅里叶特征嵌入引入输出噪声的问题,提出利用多层感知机对傅里叶特征嵌入进行鲁棒化处理,并通过定理验证其有效性,以提升下游任务性能。

摘要:

隐式神经表示(INRs)利用神经网络通过将坐标映射到目标函数的相应值来表示连续函数,其应用包括逆向图形学等。然而,在处理包含不同频率的场景时,INRs面临一种被称为频谱偏差的挑战。为克服频谱偏差,最常用的方法是基于傅里叶特征的方法,例如位置编码。然而,基于傅里叶特征的方法会给输出引入噪声,从而在应用于下游任务时降低其性能。针对这一问题,本文首先提出假设:将多层感知机(MLPs)与傅里叶特征嵌入相结合能够相互增强各自优势,但同时也会引入傅里叶特征嵌入固有的局限性。通过给出一个简单定理,我们验证了这一假设,并以此作为设计解决方案的基础。利用这些见解,我们提出使用不带加性噪声的多层感知机(MLPs)来鲁棒化傅里叶特征嵌入,从而在保持高频表示能力的同时抑制输出噪声,提升下游任务性能。

英文摘要:

Implicit Neural Representations (INRs) employ neural networks to represent continuous functions by mapping coordinates to the corresponding values of the target function, with applications e.g., inverse graphics. However, INRs face a challenge known as spectral bias when dealing with scenes containing varying frequencies. To overcome spectral bias, the most common approach is the Fourier features-based methods such as positional encoding. However, Fourier features-based methods will introduce noise to output, which degrades their performances when applied to downstream tasks. In response, this paper initially hypothesizes that combining multi-layer perceptrons (MLPs) with Fourier feature embeddings mutually enhances their strengths, yet simultaneously introduces limitations inherent in Fourier feature embeddings. By presenting a simple theorem, we validate our hypothesis, which serves as a foundation for the design of our solution. Leveraging these insights, we propose the use of multi-layer perceptrons (MLPs) without additive

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。

↑