AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Frequency-Aware Flow Matching for High-Quality Image Generation

Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen, Liang-Chieh Chen

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 1 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 low-frequency component (ablation)FreqFlow-B · ImageNet-256 ablationFID: 3.86 -> 3.55Improved
add high-frequency component (ablation)FreqFlow-B · ImageNet-256 ablationFID: 3.86 -> 3.12Improved
add both low- and high-frequency components (ablation)FreqFlow-B · ImageNet-256 ablationFID: 3.86 -> 2.95Improved
add both low- and high-frequency components (ablation)FreqFlow-B · ImageNet-256 ablationIS: 200.4 -> 231.5Improved
merge by addition instead of cross attention (ablation)FreqFlow-B · ImageNet-256 ablationFID: 3.95 -> 2.95Improved
merge by addition instead of channel concatenation (ablation)FreqFlow-B · ImageNet-256 ablationFID: 3.46 -> 2.95Improved
add loss on frequency branch (ablation)FreqFlow-B · ImageNet-256 ablationFID: 4.67 -> 2.95Improved
add loss on frequency branch (ablation)FreqFlow-B · ImageNet-256 ablationIS: 198.4 -> 231.5Improved
use unified frequency branch instead of separate networks (ablation)FreqFlow-B · ImageNet-256 ablationFID: 3.44 -> 2.95Improved
vary loss weight alpha (ablation)FreqFlow-B · ImageNet-256FIDNo clear effect
FreqFlow vs SiT frequency error (high)FreqFlow · frequency analysishigh-frequency error: 0.69 -> 0.48Improved
FreqFlow vs SiT frequency error (low)FreqFlow · frequency analysislow-frequency error: 0.08 -> 0.06Improved

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