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.

翻译：主要由于神经场的隐式特性，其缺乏直接的滤波机制，因为离散信号处理中的傅里叶分析无法直接应用于此类表示。对神经场进行有效滤波对于在下游应用中实现细节层次处理至关重要，并支持涉及在规则网格上对场进行采样的操作（例如移动立方体算法）。现有尝试在频域中分解神经场的方法要么依赖启发式算法，要么需要对神经场架构进行大规模修改。我们证明，通过简单的修改即可获得低通滤波后的神经场，并进而展示如何利用这一特性实现对整个信号的频率分解。我们通过研究细节层次重构并展示如何有效计算粗糙表示，验证了该技术的有效性。