Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SRT: Super-Resolution for Time Series via Disentangled Rectified Flow

About

Fine-grained time series data with high temporal resolution is critical for accurate analytics across a wide range of applications. However, the acquisition of such data is often limited by cost and feasibility. This problem can be tackled by reconstructing high-resolution signals from low-resolution inputs based on specific priors, known as super-resolution. While extensively studied in computer vision, directly transferring image super-resolution techniques to time series is not trivial. To address this challenge at a fundamental level, we propose Super-Resolution for Time series (SRT), a novel framework that reconstructs temporal patterns lost in low-resolution inputs via disentangled rectified flow. SRT decomposes the input into trend and seasonal components, aligns them to the target resolution using an implicit neural representation, and leverages a novel cross-resolution attention mechanism to guide the generation of high-resolution details. We further introduce SRT-large, a scaled-up version with extensive pre-training, which enables strong zero-shot super-resolution capability. Extensive experiments on nine public datasets demonstrate that SRT and SRT-large consistently outperform existing methods across multiple scale factors, showing both robust performance and the effectiveness of each component in our architecture.

Jufang Duan, Shenglong Xiao, Yuren Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Aggregated Super-ResolutionETTm1
MSE2.944
10
Aggregated Super-ResolutionETTm2
MSE1.401
10
Aggregated Super-ResolutionETTh1
MSE18.897
10
Aggregated Super-ResolutionETTh2
MSE8.248
10
Aggregated Super-ResolutionWeather
MSE2.947
10
Aggregated Super-ResolutionPEMS-SF
MSE12.542
10
Aggregated Super-ResolutionSCP1
MSE7.206
10
Aggregated Super-ResolutionCP2
MSE8.004
10
Sampled Super-ResolutionETTm1 (test)
MSE2.539
10
Sampled Super-ResolutionETTm2 (test)
MSE1.417
10
Showing 10 of 37 rows

Other info

Follow for update