Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Yo-Tin, Chen, Su-Kai, Hu, Hou-Ning, Lin, Yen-Yu, Liu, Yu-Lun
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.19706
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910030079459328
author Lin, Yo-Tin
Chen, Su-Kai
Hu, Hou-Ning
Lin, Yen-Yu
Liu, Yu-Lun
author_facet Lin, Yo-Tin
Chen, Su-Kai
Hu, Hou-Ning
Lin, Yen-Yu
Liu, Yu-Lun
contents Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR reconstruction methods through diffusion-based inpainting. Our method combines text-guided diffusion models with SDEdit refinement to generate plausible content in over-exposed areas while maintaining consistency across multi-exposure LDR images. Unlike previous approaches requiring extensive training, our method seamlessly integrates with existing HDR reconstruction techniques through an iterative compensation mechanism that ensures luminance coherence across multiple exposures. We demonstrate significant improvements in both perceptual quality and quantitative metrics on standard HDR datasets and in-the-wild captures. Results show that our method effectively recovers natural details in challenging scenarios while preserving the advantages of existing HDR reconstruction pipelines. Project page: https://github.com/EusdenLin/HDR-Reconstruction-Boosting
format Preprint
id arxiv_https___arxiv_org_abs_2602_19706
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion
Lin, Yo-Tin
Chen, Su-Kai
Hu, Hou-Ning
Lin, Yen-Yu
Liu, Yu-Lun
Computer Vision and Pattern Recognition
Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR reconstruction methods through diffusion-based inpainting. Our method combines text-guided diffusion models with SDEdit refinement to generate plausible content in over-exposed areas while maintaining consistency across multi-exposure LDR images. Unlike previous approaches requiring extensive training, our method seamlessly integrates with existing HDR reconstruction techniques through an iterative compensation mechanism that ensures luminance coherence across multiple exposures. We demonstrate significant improvements in both perceptual quality and quantitative metrics on standard HDR datasets and in-the-wild captures. Results show that our method effectively recovers natural details in challenging scenarios while preserving the advantages of existing HDR reconstruction pipelines. Project page: https://github.com/EusdenLin/HDR-Reconstruction-Boosting
title HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.19706