SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
Researchers have introduced SRT, a new framework for generating high-resolution time series data from lower-resolution inputs. SRT disentangles time series into trend and seasonal components, aligning them with target resolutions using neural representations and cross-resolution attention. A larger version, SRT-large, demonstrates strong zero-shot capabilities, outperforming existing methods across nine datasets. AI
IMPACT Introduces a novel method for improving time series data resolution, potentially benefiting applications requiring high-temporal granularity.