从标量到时间序列：重新思考时变体数据的隐式神经表示
From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric Data
浏览论文内容
中文总结 AI 辅助
本文针对时变体数据隐式神经表示优化时时空采样计算成本高的问题，提出将数据表示为空间索引时间序列，通过序列级监督训练INR，兼容多种架构，提高重建质量、降低成本，结合专家混合架构后效果更佳。
中文摘要 AI 辅助
时变体数据的隐式神经表示（INR）通常在时空坐标上进行密集采样训练，每个观测对应时空单点，这种按坐标的方式在优化时需大量采样，导致计算成本高且时间结构利用低效。本文重新审视此设计选择，表明学习时变场无需密集时空采样。而是将数据表示为空间索引时间序列集合，通过对每个空间位置的序列级监督训练INR。此重新表述消除了对密集时空采样的需求，以结构化方式从完整时间演化中学习每个空间位置。实验证明这种表示与现有INR架构兼容，能提高重建质量并显著降低训练成本。此外，还表明可与专家混合架构结合，相比基础重新表述和现有基于MoE的INR方法，MoE实例化进一步提高重建质量，在异构时间动态下提供更强的容量分配。
英文摘要
Implicit neural representations (INRs) for time-varying volumetric data are typically trained using dense sampling over spatiotemporal coordinates, where each observation corresponds to a single point in space and time. This coordinate-wise formulation requires extensive sampling during optimization, leading to high computational cost and inefficient use of temporal structure. In this work, we revisit this design choice and show that dense spatiotemporal sampling is not necessary for learning time-varying fields. Instead, we represent the data as a collection of spatially indexed time series and train INRs using sequence-level supervision over each spatial location, rather than coordinate-wise scalar samples. This reformulation eliminates the need for dense spatiotemporal sampling and instead learns each spatial location from its full temporal evolution in a structured manner. We demonstrate that this representation is compatible with a range of existing INR architectures and consistently improves reconstruction quality, while significantly reducing training cost. Furthermore, we show that this formulation can be combined with mixture-of-experts architectures, and that our MoE instantiation further improves reconstruction quality compared to both the base reformulation and existing MoE-based INR methods, providing a stronger capacity allocation under heterogeneous temporal dynamics.
发表机构
- School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）
- Department of Computer Science, Hong Kong Baptist University（香港浸会大学计算机科学系）
- Guangdong Province Key Laboratory of Computational Science（广东省计算科学重点实验室）
- National Supercomputer Center in Guangzhou（广州国家超级计算中心）
机构由 AI 辅助整理，请以论文原文为准。
