AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for Efficient HDR Reconstruction

Tao Hu, Weiyu Zhou, Yanjie Tu, Wei Dong, Peng Wu, Qingsen Yan, Yanning Zhang

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 1 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
train reconstruction branch jointly with segmentation head (DaReg-Seg) (ablation)DaReg · benchmark test setimage qualityHurt
add the degradation-aware decoder (DA Decoder) (ablation)GMODiff · benchmark test setimage qualityImproved
remove other modules one at a time (ablation)GMODiff · benchmark test setimage qualityNo clear effect
add LDM refinement on top of DaReg regression (ablation)DaReg · benchmark test setperceptual vs distortionMixed
GMODiff versus DiffHDR on perceptual qualityDiffHDR · In-distribution test splitMUSIQ: 60.39 -> 60.96Improved
GMODiff versus DiffHDRDiffHDR · In-distribution test splitPU21-PSNR: 35.43 -> 36.68Improved
GMODiff versus AFUNet on distortionAFUNet · In-distribution test splitPU21-PSNR: 36.91 -> 36.68Hurt
GMODiff versus AFUNet on perceptual DISTSAFUNet · In-distribution test splitDISTS: 0.0120 -> 0.0103Improved
GMODiff versus AFUNet on out-of-distributionAFUNet · Prabhakar datasetDISTS: 0.0589 -> 0.0379Improved
GMODiff versus AFUNet on out-of-distributionAFUNet · Prabhakar datasetPU21-PSNR: 27.78 -> 26.86Hurt
one-step denoising instead of multi-step diffusionDiffHDR · Inference 1080x1920inference time: 13.52s -> 0.93sImproved
one-step denoising versus prior LDM-based LE-DiffLE-Diff · Inference 1080x1920inference time: 132.7s -> 0.93sImproved

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