Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting

TL;DR

This paper introduces TimeGS, a novel 2D Gaussian rendering framework for time series forecasting that models future sequences as continuous surfaces, addressing limitations of previous reshaping methods and achieving state-of-the-art results.

Contribution

TimeGS shifts the forecasting paradigm to 2D generative rendering with adaptive Gaussian kernels, improving modeling of complex temporal patterns.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively models non-stationary and complex temporal variations.

Demonstrates superior adaptability over fixed-size representations.

Abstract

Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends. While recent advances have attempted to reshape 1D sequences into 2D period-phase representations, they suffer from two principal limitations.Firstly, treating reshaped tensors as static images results in a topological mismatch, as standard spatial operators sever chronological continuity at grid boundaries. Secondly, relying on uniform fixed-size representations allocates modeling capacity inefficiently and fails to provide the adaptive resolution required for compressible, non-stationary temporal patterns. To address these limitations, we introduce TimeGS, a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering. By reconceptualizing the future sequence as a continuous latent surface, TimeGS utilizes the inherent anisotropy of Gaussian kernels to adaptively model complex variations with flexible geometric alignment. To realize this, we introduce a Multi-Basis Gaussian Kernel Generation (MB-GKG) block that synthesizes kernels from a fixed dictionary to stabilize optimization, and a Multi-Period Chronologically Continuous Rasterization (MP-CCR) block that enforces strict temporal continuity across periodic boundaries. Comprehensive experiments on standard benchmark datasets demonstrate that TimeGS attains state-of-the-art performance.