ER-Diff: A Multi-Scale Exposure Residual-Guided Diffusion Model for Image Exposure Correction

Simple item page
dc.contributor.authorChen, TianZhenen_US
dc.contributor.authorLiu, Jieen_US
dc.contributor.authorRu, Yien_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:03:32Z
dc.date.available2025-10-07T06:03:32Z
dc.date.issued2025
dc.description.abstractThis paper proposes an Exposure Residual-guided Diffusion Model (ER-Diff) to address the performance limitations of existing image restoration methods in handling non-uniform exposure. Current exposure correction techniques struggle with detail recovery in extreme over/underexposed regions and global exposure balancing. While diffusion models offer powerful generative capabilities for image restoration, effectively leveraging exposure information to guide the denoising process remains underexplored. Additionally, content reconstruction fidelity in severely degraded regions is challenging to ensure. To tackle these issues, ER-Diff explicitly constructs exposure residual features to guide the diffusion process. Specifically, we design a multi-scale exposure residual guidance module that first computes the residual between the input image and an ideally exposed reference, then transforms it into hierarchical feature representations via a multi-scale extraction network, and finally integrates these features progressively into the denoising process. This design enhances feature representation in locally distorted exposure areas while maintaining global exposure consistency. By decoupling content reconstruction and exposure correction, our method achieves more natural exposure adjustment with better detail preservation while ensuring content authenticity. Extensive experiments demonstrate that ER-Diff outperforms state-of-the-art exposure correction methods in both quantitative and qualitative evaluations, particularly in complex lighting conditions, effectively balancing detail retention and exposure correction.en_US
dc.description.sectionheadersEnhancing Images
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251276
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251276
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251276
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Exposure Correction ; Diffusion Models; Multi-scale Residual Guidance
dc.subjectComputing methodologies → Exposure Correction
dc.subjectDiffusion Models
dc.subjectMulti
dc.subjectscale Residual Guidance
dc.titleER-Diff: A Multi-Scale Exposure Residual-Guided Diffusion Model for Image Exposure Correctionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20251276.pdf
Size:
9.94 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2025 Conference Papers, Posters, and Demos