[2603.02220] Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting

Computer Science > Machine Learning arXiv:2603.02220 (cs) [Submitted on 10 Feb 2026] Title:Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting Authors:Yixin Wang, Yifan Hu, Peiyuan Liu, Naiqi Li, Dai Tao, Shu-Tao Xia View a PDF of the paper titled Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting, by Yixin Wang and 5 other authors View PDF HTML (experimental) 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 this http URL, 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 introdu...