In response to several key challenges faced by the existing tone mapping techniques in practical applications, such as insufficient stability of mapping results, difficulty in balancing the natural aesthetics of images, and limited adaptability to complex lighting environments and diverse scene types, this paper proposes a tone mapping method based on multimodal learning. The goal is to acquire cross-modal supervisory information through the shared semantic space of text and images, aiming to achieve more accurate, natural, and universally applicable tone mapping. By leveraging the text-image matching information from large text-image models to assist in unsupervised training, the method effectively suppresses the occurrence of underexposed and overexposed areas, avoiding the training instability and complexity issues present in generative adversarial methods and contrastive learning. Experiments demonstrate that the proposed tone mapping method displays superior performance across multiple open benchmark datasets. Compared with the existing mainstream tone mapping algorithms, this method not only maintains the overall lighting atmosphere of images but also more effectively suppresses overexposed areas, enhances underexposed areas, retains rich color details, and enhances visual hierarchy, with stronger adaptability to various lighting conditions and scene types. Moreover, this work also confirms the significant potential of multimodal learning in foundational vision tasks.
KALANTARIN K, RAMAMOORTHIR. Deep high dynamic range imaging of dynamic scenes[J]. ACM Transactions on Graphics, 2017, 36(4): 1-12.
[2]
DRAGOF, MYSZKOWSKIK, ANNENT,et al .Adaptive logarithmic mapping for displaying high contrast scenes[J].Computer Graphics Forum,2003,22(3): 419-426.
[3]
FATTALR, LISCHINSKID, WERMANM .Gradient domain high dynamic range compression[M]//Seminal graphics papers:pushing the boundaries:volume 2.New York,NY,USA:ACM,2023:671-678.
[4]
REINHARDE, STARKM, SHIRLEYP,et al .Photographic tone reproduction for digital images[M]//Seminal graphics papers:pushing the boundaries:volume 2.New York,NY,USA:ACM,2023:661-670.
[5]
LIANGZ T, XUJ, ZHANGD,et al .A hybrid l1-l0 layer decomposition model for tone mapping[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,UT,USA. IEEE,2018:4758-4766.
[6]
SHIBATAT, TANAKAM, OKUTOMIM .Gradient-domain image reconstruction framework with intensity-range and base-structure constraints[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas,NV,USA. IEEE,2016:2745-2753.
[7]
HOUX X, DUANJ, QIUG P .Deep feature consistent deep image transformations:downscaling,decolorization and HDR tone mapping[EB/OL].(2017-09-11)[2024-01-10]2017:1707. 09482.org/abs/1707.09482v2.
[8]
JOHNSONJ, ALAHIA, LIF F .Perceptual losses for real-time style transfer and super-resolution[M]//Computer vision-ECCV 2016. Cham: Springer International Publishing,2016:694-711.
[9]
GHARBIM, CHENJ W, BARRONJ T,et al .Deep bilateral learning for real-time image enhancement[J].ACM Transactions on Graphics,2017,36(4):1-12.
[10]
MONTULETR, BRIASSOULIA. Deep learning for robust end-to-end tone mapping[C]//30th British Machine Vision Conference. BMVA Press, 2020: 160373.
[11]
RANAA, SINGHP, VALENZISEG, et al. Deep tone mapping operator for high dynamic range images[J]. IEEE Transactions on Image Processing,2019,29:1285-1298.
[12]
ZHANGN, WANGC, ZHAOY,et al. Deep tone mapping network in HSV color space[C]//2019 IEEE Visual Communications and Image Processing (VCIP). Sydney,Australia. IEEE,2019:1-4.
[13]
PATELV A, SHAHP, RAMANS. A generative adversarial network for tone mapping HDR images[M]//Computer vision,pattern recognition,image processing,and graphics.Singapore:Springer Singapore,2018:220-231.
[14]
CAOX, LAIK, YANUSHKEVICHS N,et al .Adversarial and adaptive tone mapping operator for high dynamic range images[C]//2020 IEEE Symposium Series on Computational Intelligence (SSCI). Canberra,ACT,Australia. IEEE, 2020: 1814-1821.
[15]
ISOLAP, ZHUJ Y, ZHOUT H,et al .Image-to-image translation with conditional adversarial networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 5967-5976.
[16]
YEGANEHH, WANGZ .Objective quality assessment of tone-mapped images[J].IEEE Transactions on Image Processing,2013, 22(2): 657-667.
[17]
VINKERY, HUBERMAN-SPIEGELGLASI, FATTALR .Unpaired learning for high dynamic range image tone mapping[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal,QC,Canada. IEEE,2021:14637-14646.
[18]
CAOC, YUEH J, LIUX,et al .Unsupervised HDR image and video tone mapping via contrastive learning[J].IEEE Transactions on Circuits and Systems for Video Technology,2024,34(2):786-798.
[19]
RADFORDA, KIMJ W, HALLACYalC, et al. Learning transferable visual models from natural language supervision[C]//International conference on machine learning. PMLR, 2021: 8748-8763.
[20]
LIANGZ X, LIC Y, ZHOUS C,et al .Iterative prompt learning for unsupervised backlit image enhancement[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris,France. IEEE,2023:8060-8069.
[21]
RONNEBERGERO, FISCHERP, BROXT. U-Net:convolutional networks for biomedical image segmentation[M]//Medical image computing and computer-assisted intervention-MICCAI 2015.Cham:Springer International Publishing, 2015: 234-241.
[22]
PANETTAK, KEZEBOUL, OLUDAREV,et al .TMO-net:a parameter-free tone mapping operator using generative adversarial network,and performance benchmarking on large scale HDR dataset[J].IEEE Access, 2021, 9: 39500-39517.
[23]
WANGZ, BOVIKA C, SHEIKHH R,et al .Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[24]
HASINOFFS W, SHARLETD, GEISSR,et al .Burst photography for high dynamic range and low-light imaging on mobile cameras[J]. ACM Transactions on Graphics,2016,35(6):1-12.
[25]
AGUSTSSONE, TIMOFTER .NTIRE 2017 challenge on single image super-resolution:dataset and study[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Honolulu,HI,USA. IEEE,2017:1122-1131.
[26]
Hdri-haven[EB/OL]. (2024-11-3)[2025-05-13].
[27]
FAIRCHILDM D .The HDR photographic survey[J]. Color and Imaging Conference,2007,15(1): 233-238.
[28]
GUK, WANGS Q, ZHAIG T,et al .Blind quality assessment of tone-mapped images via analysis of information,naturalness,and structure[J].IEEE Transactions on Multimedia,2016,18(3):432-443.
[29]
LEC Y, YANJ B, FANGY M,et al .Perceptually optimized deep high-dynamic-range image tone mapping[EB/OL]. (2021-09-11)[2024-01-10].