Largely due to their implicit nature, neural fields lack a direct mechanism
for filtering, as Fourier analysis from discrete signal processing is not
directly applicable to these representations. Effective filtering of neural
fields is critical to enable level-of-detail processing in downstream
applications, and support operations that involve sampling the field on regular
grids (e.g. marching cubes). Existing methods that attempt to decompose neural
fields in the frequency domain either resort to heuristics or require extensive
modifications to the neural field architecture. We show that via a simple
modification, one can obtain neural fields that are low-pass filtered, and in
turn show how this can be exploited to obtain a frequency decomposition of the
entire signal. We demonstrate the validity of our technique by investigating
level-of-detail reconstruction, and showing how coarser representations can be
computed effectively.

通过简单修改，我们可以获得经过低通滤波的神经场，并展示如何利用此技术获得整个信号的频率分解，从而有效地计算出更粗糙的表示形式。