AI Paper Atlas

Research map / Image generation / Super-resolution

GenDR: Lighten Generative Detail Restoration

Yan Wang, Shijie Zhao, Kexin Zhang, Junlin Li, Li zhang

ICLR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution

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
use CiD instead of VSD for step distillation (ablation)GenDR · RealSRMUSIQ: 65.01 -> 66.85Improved
use CiD instead of SiD for step distillation (ablation)GenDR · RealSet80MUSIQ: 69.33 -> 70.61Improved
add adversarial loss to CiD (ablation)GenDR · RealSRClipIQA / LPIPS: ClipIQA 0.6532 -> 0.7020; LPIPS 0.2527 -> 0.2899Mixed
add representation alignment (REPA) loss to CiD+adv (ablation)GenDR · RealSRMUSIQ: 68.30 -> 68.36No clear effect
use CiDA instead of VSD (ablation)OSEDiff and GenDR · Q-AlignQ-Align: +0.08Improved
use 16-channel VAE (SD2.1-VAE16) instead of 4-channel VAE for super-resolution (ablation)GenDR base model · RealSR / RealSet80IQA scoresImproved
use 16-channel VAE instead of 4-channel for text-to-image generation (ablation)SD2.1 · COCO 2014 20k promptsFID: 13.45 -> 27.89Hurt
replace text encoder and scheduler with fixed prompt embeddings (ablation)GenDR pipeline · RealLR200ClipIQA / MUSIQNo clear effect
use N3 negative prompt versus other negative prompts (ablation)GenDR fixed prompts · RealLRClipIQA / MUSIQ: average 0.7231/71.58 vs Null 0.7193/71.40Improved
use LoRA and shared base model for score networks with CiDA (ablation)CiDA training · training costtime per iteration: memory comparable to VSD; training steps slower by 34% (CiD) and 42% (CiDA)Mixed
GenDR one-step versus DreamClear multi-stepGenDR · inference speedspeedup: about 89.5x acceleration with half the parametersImproved

Later papers that compared with this method

1 later accepted paper reports GenDR-1 as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

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