基于掩模Transformer的HDR图像重建算法  

HDR Image Reconstruction Algorithm Based on Masked Transformer

作　　者：张祖珩 陈晓冬[1] 汪毅[1] 蔡怀宇[1] Zhang Zuheng;Chen Xiaodong;Wang Yi;Cai Huaiyu(Key Laboratory of Opto-Electronics Information Technology of Ministry of Education,College of Precision Instrument and Opto-Electronic Engineering,Tianjin University,Tianjin 300072,China)

机构地区：[1]天津大学精密仪器与光电子工程学院光电信息技术教育部重点实验室,天津300072

出　　处：《激光与光电子学进展》2025年第2期399-410,共12页Laser & Optoelectronics Progress

基　　金：国家自然科学基金重大科研仪器研制项目(82027801)。

摘　　要：在众多高动态范围(HDR)图像重建算法中,生成包围曝光式的HDR图像重建算法因其突出的动态范围扩展能力及对复杂光照场景的适应能力成为研究的热点。然而,生成包围曝光式重建算法往往基于卷积神经网络构建图像生成器,导致生成器仅具有局部感受野,难以利用全局信息,使图像过曝与欠曝区域信息恢复能力受限。为此,本文引入Transformer架构赋予网络全局感受野,增强网络建立长距离依赖的能力。同时,为Transformer添加单向软掩模,避免过曝与欠曝区域的无效信息向特征图输入噪声,进一步提高重建质量。实验结果表明,所提算法在VDS数据集与HDREye数据集上峰值信噪比分别提高2.37 dB和1.33 dB,主观对比实验进一步证明所提算法的有效性。该研究为提升HDR图像重建算法对过曝与欠曝区域的信息恢复能力提供了一种新的思路。High-dynamic range(HDR)image reconstruction algorithms based on the generation of bracketed image stacks have gained popularity for their capabilities in expanding the dynamic range and adapting to complex lighting scenarios.However,existing approaches based on convolutional neural networks often suffer from local receptive fields,limiting the utilization of global information and recovery of over-or underexposed regions.To solve this problem,this study introduces a Transformer architecture that equips the network with a global receptive field to establish long-range dependency.In addition,a unidirectional soft mask is added to the Transformer to alleviate the effects of invalid information from over-and underexposed regions,further improving the reconstruction quality.Experimental results show that the proposed algorithm improves the peak signal-to-noise ratio by 2.37 dB and 1.33 dB on the VDS and HDREye datasets,respectively,and subjective comparisons further prove the effectiveness of the proposed algorithm.This study provides a novel approach for improving the information recovery capabilities of HDR image reconstruction algorithms for over-and underexposed regions.

关 键 词：高动态范围图像重建 深度学习 软掩模 TRANSFORMER 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]