AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

ColorFM: An Optimization-to-Learning Framework for Color Transfer via Flow Matching

Yuhang He, Kai Zhang, Xiaoming Li, Du Chen, Jian Yang

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 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
increase subdivision depth Dmax from 0 to 3 (ablation)hierarchical color coupling · ColorFM-O coupling ablationLipschitz: 5.811 -> 2.937Improved
increase Dmax from 3 to 5 (ablation)hierarchical color coupling · ColorFM-O coupling ablationStyle similarity / time: 0.779 -> 0.773; 19.26 -> 24.37 sHurt
use hierarchical coupling (Dmax=3) instead of 2-Rectified Flow (ablation)ColorFM-O · ColorFM-O coupling ablationStyle similarity: 0.738 -> 0.779Improved
use hierarchical coupling instead of Mini-Batch OT (ablation)ColorFM-O · ColorFM-O coupling ablationTime (s): 51.48 -> 19.26Improved
add explicit semantic alignment (ablation)ColorFM-O · color transferqualitativeImproved
use bidirectional instead of direct transport (ablation)ColorFM-L · ColorFM-L component ablationDistance to Ideal: 0.339 -> 0.326Improved
add fixed state (ablation)ColorFM-L · ColorFM-L component ablationDistance to Ideal: 0.326 -> 0.334Hurt
add implicit state with concat fusion (ablation)ColorFM-L · ColorFM-L component ablationDistance to Ideal: 0.326 -> 0.331No clear effect
use cross-attention instead of concat fusion for implicit state (ablation)ColorFM-L · ColorFM-L component ablationDistance to Ideal: 0.331 -> 0.320Improved
train ColorFM-L on ColorFM-O pseudo pairs instead of instance optimizationColorFM-O · color transfer (512x512)Distance to Ideal: 0.338 -> 0.320Improved
degrade semantic masks by 20% misclassification (ablation)ColorFM-O · semantic mask robustnessStyle similarity: 0.745 -> 0.731No clear effect
degrade semantic masks by 60% misclassification (ablation)ColorFM-O · semantic mask robustnessStyle similarity: 0.745 -> 0.695Hurt

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