AI Paper Atlas

Research map / Image generation / Super-resolution

TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution

Zhiqiang Wu, Yitong Dong, Xian Wei

CVPR 2026 · Image generation › Super-resolution · approach: Diffusion-based 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
split x4 SR into two x2 stages (M2N2) rather than single x4 stage (ablation)TUDSR-S · RealSR x4MUSIQ: 69.2568 -> 70.2406Improved
split x4 SR into two x2 stages (ablation)TUDSR-S · RealLQ250 x4MUSIQ: 70.4876 -> 71.9250Improved
split x4 SR into two x2 stages (ablation)TUDSR-S · RealSR x4MANIQA: 0.6818 -> 0.6786Hurt
split x4 SR into two x2 stages (ablation)TUDSR-S · RealLQ250 x4NIQE: 3.5207 -> 3.9440Hurt
use stage-2 LoRA only (N4) instead of two-stage (ablation)TUDSR-S · RealSR x4MUSIQ: 28.5303 vs 70.2406Hurt
split x8 SR into x4 then x2 (M4N2) rather than single x8 stage (ablation)TUDSR-S · RealLQ250 x8MUSIQ: 51.5389 -> 63.2129Improved
split x8 SR into x4 then x2 (ablation)TUDSR-S · RealSR x8MUSIQ: 65.7316 -> 67.2225Improved
split x8 SR into x4 then x2 (ablation)TUDSR-S · RealSR x8NIQE: 4.4895 -> 4.6839Hurt
split x8 SR into x4 then x2 (ablation)TUDSR-S · DrealSR x8NIQE: 5.3613 -> 5.5417Hurt
use stage-2 LoRA only (N8) instead of two-stage (ablation)TUDSR-S · RealLQ250 x8MUSIQ: 19.6954 vs 63.2129Hurt
compare TUDSR-S with OSEDiff on x8 SRTUDSR-S vs OSEDiff · RealLQ250 x8MUSIQ: 54.8024 -> 63.2129Improved
compare TUDSR-S with strongest one-step baseline on x4TUDSR-S vs PiSA-SR · RealSR x4FID: 124.19 -> 111.42Improved

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