2026-10-10T03:01:41Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33956773 2026-09-21T17:37:28Z category_146 category_21 category_734 category_931 category_811 portal_5 item_type_3 month_year_09_2026

<p>Evaluation metrics used in this paper.</p> Chunmeng Wang (8669721) Wenxiang Zhang (600021) Quan Zhang (168081) Siyi Zhou (15217838) Space Science Biotechnology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Mathematical Sciences not elsewhere classified several merger blocks qualitative experiments conducted natural color restoration methods often struggle fields like photography experimental results show based method swinfusion 5 %, 19 medical image processing image structural similarity high dynamic range color enhancement branch global dependency modeling simultaneously preserve local div >< p 8 %, 2 branch network consisting based metric mef local feature extraction three mef datasets image feature feature extraction branch network estimate high transformer branch global features upsampling operation resolution weights ranks second oriented metrics merging module inherent correlation human perception guided filtering exposure fusion chrominance information chrominance components art transformer <div><p>High dynamic range (HDR) imaging is crucial in fields like photography and medical image processing. Traditional multi-exposure fusion (MEF) methods often struggle to simultaneously preserve local and global features as well as chrominance information. To address this issue, we propose MEF-TBN, a three-branch network consisting of a context aggregation attention network (CAAN) branch for local feature extraction, a transformer branch for global dependency modeling, and a color enhancement branch for natural color restoration. Specifically, the CAAN and transformer branches generate low-resolution weight maps based on local and global features of luminance components, and a merging module is proposed to refine and enhance the local and global features with several merger blocks, and then estimate high-resolution weights by adopting the guided filtering for upsampling operation. Meanwhile, the color enhancement branch is capable of learning the inherent correlation between luminance and chrominance components. Experimental results show that compared with 9 representative MEF methods, our method achieves optimal performance on most image feature-based metrics including AG, EI and SF, as well as all human perception-oriented metrics such as Q^CB, VIF and NIQE, and ranks second in the image structural similarity-based metric MEF-SSIM. In particular, compared with the state-of-the-art transformer-based method SwinFusion, our method achieves average performance improvements of 11.5%, 19.8%, 2.2% and 1.6% on Q^CB, VIF, NIQE and MEF-SSIM metrics, respectively. Both quantitative and qualitative experiments conducted on three MEF datasets with different input exposure numbers demonstrate that the proposed method achieves superior performance than the other methods.</p></div> 2026-09-21T17:37:09Z Dataset Dataset 10.1371/journal.pone.0357156.t002 https://figshare.com/articles/dataset/_p_Evaluation_metrics_used_in_this_paper_p_/33956773 CC BY 4.0