AI Paper Atlas

Research map / Image generation / Super-resolution

DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer

Qingji Dong, Hang Dong, Mingqin Chen, Rui Zhang, Yitong Wang

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
add dual-branch MM-ControlNet text branch with global+local prompts (vs global prompt only) (ablation)DreamSR · RealDegMUSIQ: 41.6816 -> 45.6234Improved
add dual-branch MM-ControlNet (vs patch prompt only) (ablation)DreamSR · RealDegMUSIQ: 41.5523 -> 45.6234Improved
add dual-branch MM-ControlNet (vs global prompt only) (ablation)DreamSR · RealDegMANIQA: 0.3891 -> 0.4574Improved
add image-to-image (i2i) degradation pipeline to training (ablation)DreamSR · RealDegMUSIQ: 43.7706 -> 45.6234Improved
add i2i degradation pipeline (ablation)DreamSR · RealDegCLIPIQA+: 0.6355 -> 0.6647Improved
add Receptive-Field Enhancement training (512 native-HR patches) (ablation)DreamSR · RealDegMUSIQ: 43.5546 -> 45.6234Improved
add Receptive-Field Enhancement training (ablation)DreamSR · RealDegCLIPIQA+: 0.5975 -> 0.6647Improved
add Restoration Acceleration LoRA with 1+16 steps (vs 20 steps without) (ablation)DreamSR · RealDegMUSIQ: 37.9976 -> 43.7706Improved
add Restoration Acceleration LoRA with 1+16 steps (vs 30 steps without) (ablation)DreamSR · RealDegMUSIQ: 38.3402 -> 43.7706Improved
add Restoration Acceleration LoRA (ablation)DreamSR · RealDegCLIPIQA+: 0.6042 -> 0.6355Improved
DreamSR vs BSRGAN on reference metricDreamSR · RealSRPSNR: 26.3785 -> 20.9305Hurt
DreamSR vs best baseline on no-reference metricDreamSR · RealSRMUSIQ: 69.8241 -> 70.5560Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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