AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

HDR Image Generation via Gain Map Decomposed Diffusion

Yuanshen Guan, Ruikang Xu, Yinuo Liao, Mingde Yao, Lizhi Wang, Zhiwei Xiong

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 2 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 brightness-aware compression instead of hard clipping (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationFHLP: 0.0036 -> 0.1009Improved
add brightness-aware compression instead of hard clipping (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationNIQE: 8.1674 -> 6.4392Improved
add brightness-aware compression instead of fixed mu-law (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationEHL: 0.5897 -> 0.7051Improved
add brightness-aware compression instead of fixed mu-law (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationFHLP: 0.0855 -> 0.1009Improved
add gamut-constrained reduction (gamut loss) (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationFWGP: 0.0010 -> 0.0058Improved
add gamut-constrained reduction (gamut loss) (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationNIQE: 7.2908 -> 6.4392Improved
add gamut-constrained reduction (gamut loss) (ablation)triplet construction · MSCOCO subset (5,000 samples), degradation ablationBRISQUE: 30.6521 -> 27.2434Improved
use gain map diffusion instead of SD+KUNet pipelineHDR image generation · HDR generation (4,000 landscape samples)EHL: 0.0575 -> 0.0900Improved
use gain map diffusion instead of SD+KUNet pipelineHDR image generation · HDR generation (4,000 landscape samples)FHLP: 0.5764 -> 0.6318Improved
use gain map diffusion instead of KUNetSDR-to-HDRTV up-conversion · HDRTV1K SDR-to-HDRTV up-conversionEWG: 0.0006 -> 0.0295Improved
use gain map diffusion instead of HDRTVNetSDR-to-HDRTV up-conversion · HDRTV1K SDR-to-HDRTV up-conversionHDRVDP3: 8.4642 -> 7.4771Hurt
use gain map diffusion instead of best baselineSDR-to-HDRTV up-conversion · HDRTV1K SDR-to-HDRTV up-conversionluminance range extension and color gamut coverage: 3.77× and 6.02×Improved

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