AI Paper Atlas

Research map / Image generation / Super-resolution

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

Jufang Duan, Shenglong Xiao, Yuren Zhang

ICLR 2026 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the implicit time function (ITF) (ablation)SRT · ETTm1 SSRMSE / DTW gap: +0.011 / +0.006Improved
add the implicit time function (ITF) (ablation)SRT · weather SSRMSE / DTW gap: +0.021 / +0.018Improved
add pattern smoothness in ITF (ablation)SRT · PEMS-SF SSRMSE / DTW gap: +0.017 / +0.015Improved
add the ITF multi-stage schema (ablation)SRT · PEMS-SF SSRMSE / DTW gap: +0.014 / +0.008Improved
add RoPE in the velocity predictor (ablation)SRT · PEMS-SF SSRMSE / DTW gap: +0.032 / +0.019Improved
add Pre-LN in the velocity predictor (ablation)SRT · weather SSRMSE / DTW gap: +0.018 / +0.011Improved
add the second CRA layer (attention to low-resolution series) (ablation)SRT · weather SSRMSE / DTW gap: +0.031 / +0.026Improved
add both cross-resolution attention layers (ablation)SRT · weather SSRMSE / DTW gap: +0.029 / +0.052Improved
disentangle detail and low-resolution into trend and periodic components (ablation)SRT · PEMS-SF SSRMSE / DTW gap: +0.046 / +0.073Improved
use the proposed velocity predictor instead of MLP (ablation)SRT · PEMS-SF SSRMSE gap: +0.203Improved
use the proposed velocity predictor instead of vanilla Transformer (ablation)SRT · ETTm1 SSRMSE / DTW gap: +0.085 / +0.048Improved
use TCN predictor instead of proposed predictor (ablation)SRT · ETTm1 SSRMSE / DTW gap: +0.002 / +0.001No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy