Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Neural Processes (NPs), which model the distributions over functions conditioned on partial observations (context set), provide a practical solution for fast inference of continuous functions. However, existing NP architectures suffer from inferior modeling capability for complex signals. In this paper, we propose an efficient NP framework dubbed Versatile Neural Processes (VNP), which largely increases the capability of approximating functions. Specifically, we introduce a bottleneck encoder that produces fewer and informative context tokens, relieving the high computational cost while providing high modeling capability. At the decoder side, we hierarchically learn multiple global latent variables that jointly model the global structure and the uncertainty of a function, enabling our model to capture the distribution of complex signals. We demonstrate the effectiveness of the proposed VNP on a variety of tasks involving 1D, 2D and 3D signals. Particularly, our method shows promise in learning accurate INRs w.r.t. a 3D scene without further finetuning. Code is available at https://github.com/ZongyuGuo/Versatile-NP .

翻译：近年来，将信号表示为神经网络参数化的连续函数（即隐式神经表征，INRs）受到越来越多的关注。神经过程（NPs）通过在部分观测（上下文集合）条件下建模函数分布，为连续函数的快速推断提供了实用解决方案。然而，现有NP架构在复杂信号的建模能力上仍显不足。本文提出一种名为高效神经过程（VNP）的高效NP框架，显著提升了函数逼近能力。具体而言，我们引入了一种瓶颈编码器，能够生成数量更少且信息密度更高的上下文标记，在降低计算开销的同时保持高建模能力。在解码器端，我们分层学习多个全局隐变量，共同建模函数的全局结构与不确定性，使模型能够捕获复杂信号的分布。我们在涉及一维、二维及三维信号的多种任务上验证了VNP的有效性。特别地，我们的方法无需额外微调即可学习精确的三维场景隐式神经表征。代码开源在：https://github.com/ZongyuGuo/Versatile-NP