Journal of Zhejiang University

ENGINEERING Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Unsupervised Single-Image High Dynamic Range Rendering via Multi-Exposure Priors

Author(s): Han Wang¹, Bolun Zheng¹, Quan Chen², Qianyu Zhang¹, Tao Zhang¹, Jiyong Zhang¹, Xiang Tian³
Affiliation(s): ¹School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China ²The College of Artificial Intelligence, Jiaxing University, Jiaxing 314001, China ³The Institute of Advanced Digital Technology and Instrument, Zhejiang University, Hangzhou 310027, China
Corresponding email(s): Quan Chen, chenquan@alu.hdu.edu.cn
Key Words: HDR reconstruction; Single image HDR; Unsupervised learning; Multi-exposure prior

Share this article to： More <<< Previous Paper \|Next Paper >>>

Han Wang¹, Bolun Zheng¹, Quan Chen², Qianyu Zhang¹, Tao Zhang¹, Jiyong Zhang¹, Xiang Tian³. Unsupervised Single-Image High Dynamic Range Rendering via Multi-Exposure Priors[J]. Journal of Zhejiang University Science ,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/ENG.ITEE.2025.0116

@article{title="Unsupervised Single-Image High Dynamic Range Rendering via Multi-Exposure Priors",
author="Han Wang¹, Bolun Zheng¹, Quan Chen², Qianyu Zhang¹, Tao Zhang¹, Jiyong Zhang¹, Xiang Tian³",
journal="Journal of Zhejiang University Science ",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/ENG.ITEE.2025.0116"
}

%0 Journal Article
%T Unsupervised Single-Image High Dynamic Range Rendering via Multi-Exposure Priors
%A Han Wang¹
%A Bolun Zheng¹
%A Quan Chen²
%A Qianyu Zhang¹
%A Tao Zhang¹
%A Jiyong Zhang¹
%A Xiang Tian³
%J Journal of Zhejiang University SCIENCE
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/ENG.ITEE.2025.0116"

TY - JOUR
T1 - Unsupervised Single-Image High Dynamic Range Rendering via Multi-Exposure Priors
A1 - Han Wang¹
A1 - Bolun Zheng¹
A1 - Quan Chen²
A1 - Qianyu Zhang¹
A1 - Tao Zhang¹
A1 - Jiyong Zhang¹
A1 - Xiang Tian³
J0 - Journal of Zhejiang University Science
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/ENG.ITEE.2025.0116"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Reconstructing high dynamic range (HDR) images from a single low dynamic range (LDR) input requires recovering missing information in highlight-clipped and shadow-distorted regions. Existing methods generally rely on sufficient groundtruth HDR images as supervision signals or multi-exposure LDR sequences to improve quality, limiting their flexibility. To address this, we propose USME-HDR, a framework for single-image HDR reconstruction based on multi-exposure priors, where the HDR reconstruction stage is learned without ground-truth HDR supervision. Specifically, an Exposure-Adjustment Network (EAN) is trained in a supervised manner to map a single LDR image to over/under-exposure pairs. Inspired by Retinex theory, we further decompose the input into Light Map and Light Feature, which are fed into EAN as auxiliary inputs for luminanceaware exposure generation. An exposure ratio guidance mechanism is further introduced to improve luminance fidelity. Finally, the HDR image is synthesized by fusing the original LDR image with generated multi-exposure images, refined through selfsupervised optimization. Experiments demonstrate that, during the testing phase, USME-HDR reconstructs visually compelling HDR images from only a single LDR input, without requiring real low- or high-exposure images.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Full Text: <7>

CLC number:

On-line Access: 2026-05-07

Received: 2025-11-04

Revision Accepted: 2026-04-19

Crosschecked: 0000-00-00

Cited: 0

Clicked: 17

Citations: Bibtex RefMan EndNote GB/T7714

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

- Go to