AI Paper Atlas

Research map / Image generation / Super-resolution

Consistency Trajectory Matching for One-Step Generative Super-Resolution

Weiyi You, Mingyang Zhang, Leheng Zhang, Xingyu Zhou, Kexuan Shi, Shuhang Gu

ICCV 2025 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 12 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 Distribution Trajectory Matching loss to consistency training (ablation)CTMSR · ImageNet-TestCLIPIQA: 0.6092 -> 0.6913Improved
add Distribution Trajectory Matching loss to consistency training (ablation)CTMSR · ImageNet-TestMUSIQ: 56.650 -> 60.142Improved
add DTM loss (ablation)CTMSR · ImageNet-TestPSNR: 24.71 -> 24.73Improved
use score distillation sampling loss instead of DTM (ablation)CTMSR · ImageNet-TestPSNR: 24.71 -> 23.17Hurt
use SDS instead of consistency training alone (ablation)CTMSR · ImageNet-TestMUSIQ: 56.650 -> 58.188Improved
replace SDS by DTM (ablation)CTMSR · ImageNet-TestMUSIQ: 58.188 -> 60.142Improved
one-step distillation-free consistency training instead of distilling ResShift (SinSR)one-step SR · ImageNet-TestMUSIQ: 53.632 -> 60.142Improved
one-step CTMSR versus SinSR on real dataRealSR · RealSRCLIPIQA: 0.6627 -> 0.6449Hurt
one-step CTMSR versus ResShift-4 on fidelityImageNet-Test · ImageNet-TestPSNR: 25.02 -> 24.73Hurt
reduce inference to one step (CTMSR-1 versus ResShift-15)inference runtime · 64x64 input RTX3090runtime (ms): 689 -> 48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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