Abstract
Ghost removal in high dynamic range imaging is a challenging problem especially when relative camera or object motion exists. To solve the problem, an effective coarse-to-fine deghosting method combining registration and matching based on PatchMatch is proposed. Firstly, the coarse registration scheme based on Scale-Invariant Feature Transform is used to achieve the consistency of image scale space. Secondly, similarity measure of underlayer information is established by Mutual Information to realize fine registration. Thirdly, different from general distance measurement, structural similarity index measurement is employed to build the objective function to search for the best-matched patch in the fusion process. Experimental results demonstrate the algorithm can remove the ghost artifacts effectively. Furthermore, objective evaluations show that the algorithm accuracy has been improved comprehensively. Compared with the existing methods, the proposed algorithm can achieve a convincing result for dynamic senses, especially for large moving objects.
Similar content being viewed by others
References
Niu, Y., Wu, J., Liu, W., et al.: Hdr-gan: Hdr image reconstruction from multi-exposed ldr images with large motions. IEEE Trans. Image Process. 45, 3885–3896 (2020)
Liao, X., Li, K., Zhu, X., et al.: Robust detection of image operator chain with two-stream convolutional neural network. IEEE J. Sel. Topics Signal Process. 14(5), 955–968 (2020)
Lee, S., An, G. H., Kang, S.-J.: “Deep recursive hdri: Inverse tone mapping using generative adversarial networks,” In: proceedings of the European Conference on Computer Vision (ECCV), 596–611 (2018)
Rana, A., Singh, P., Valenzise, G., et al.: Deep tone mapping operator for high dynamic range images. IEEE Trans. Image Process. 25, 99 (2019)
Yin, J.-L., Chen, B.-H., Peng, Y.-T.: Two exposure fusion using prior-aware generative adversarial network. IEEE Trans. Multim. 871, 1–1 (2021)
Yin, J.L., Chen, B.H., Peng, Y.T., et al.: Automatic intermediate generation with deep reinforcement learning for robust two-exposure image fusion. IEEE Trans. Neural Netw. Learn. Syst. 99, 1–10 (2021)
Ma, K., Duanmu, Z., Yeganeh, H., et al.: Multi-exposure image fusion by optimizing a structural similarity index. IEEE Trans. Comput Imag. 4(1), 60–72 (2017)
Liao, X., Yin, J., Chen, M., et al.: Adaptive payload distribution in multiple images steganography based on image texture features. IEEE Trans. Dependable Secure Comput. 24, 1 (2020)
Liao, X., Yu, Y., Li, B., et al.: A new payload partition strategy in color image steganography. IEEE Trans. Circuit Syst. Video Technol. 30(3), 685–696 (2020)
Mertens, T., Kautz, J., Van, R.F.: Exposure fusion: a simple and practical alternative to high dynamic range photography. Comput. Graph Forum. 28(1), 161–171 (2009)
Rui, S., Cheng, I., S, J., et al.: Generalized random walks for fusion of multi-exposure images. IEEE Trans. Image Process. 20(12), 3634–3646 (2011)
Lee, C., Li, Y., Monga, V.: Ghost-free high dynamic range imaging via rank minimization. IEEE Signal Process. Lett. 21(9), 1045–1049 (2014)
Hu, J., Gallo, O., Pulli, K., et al.: “Hdr deghosting: How to deal with saturation?,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Portland., 1164–1170 (2013)
Wang, Z., Bovik, A.C., Sheikh, H.R., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Heo, Y. S., Lee, S. U., K. M., Lee, “Ghost-free high dynamic range imaging,” in Proc. Conf. on Comp. Vision., San Francisco., 486–500 (2010)
Gallo, O., Troccoli, A., Hu, J., et al.: “Locally non-rigid registration for mobile hdr photography,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Boston., wos:000378887900101 (2015)
Qin, X., Shen, J., Mao, X., et al.: Robust match fusion using optimization. IEEE Trans. Cybern. 45(8), 1549–1560 (2015)
Sen, P., Kalantari, N.K., Yaesoubi, M., et al.: Robust patch-based hdr reconstruction of dynamic scenes. ACM Trans. Graph. 31(6), 541 (2012). https://doi.org/10.1145/23661452366222
Kalantari, N.K., Ramamoorthi, R.: Deep high dynamic range imaging of dynamic scenes. ACM Trans. Graph. 36(4), 1–12 (2017)
Yan, Q., Gong, D., Shi, Q., et al.: “Attention-guided network for ghost-free high dynamic range imaging,” In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Los Angeles., 1851–1760 (2019)
Huang, W., Zhang, W., Pan, L., et al.: “Image fusion localization algorithm based on sift and 3d model,” In: Seventh Symposium on Novel Photoelectronic Detection Technology and Application 2020, (2021)
Wang, L., Chang, C., Liu, Z., et al.: A medical image fusion method based on sift and deep convolutional neural network in the sist domain. J. Healthcare Eng. 2021, 9958017 (2021)
Pluim, J.P.W., Maintz, J., Viergever, M.A.: Mutual-information-based registration of medical images: a survey. IEEE Trans. Med Imag. 22(8), 986–1004 (2003)
C. available HDR processing software, “Photomatix,” (2012)
Tursun, O.T., Akyüz, A., Erdem, A., et al.: An objective deghosting quality metric for hdr images. IEEE Signal Process Lett. 35(2), 139–152 (2016)
Sheikh, H.R., Bovik, A.C.: Image information and visual quality. IEEE Trans. Image Process. 15(2), 430–444 (2006)
Baroncini, V., Capodiferro, L., Di, E. D.: “The polar edge coherence: A quasi blind metric for video quality assessment,” In: European Signal Processing Conference, Nice., 564–568 (2015)
Yeganeh, H., Wang, Z.: Objectsive quality assessment of tone-mapped images. IEEE Trans. Image Process. 22(2), 657–667 (2012)
Mittal, A., Soundararajan, R., Bovik, A.C.: Making a completely blind image quality analyzer. IEEE Signal Process Lett. 22(3), 209–213 (2012)
Xia, X., Yao, Y., Liang, J., et al.: Evaluation of focus measures for the autofocus of line scan cameras. Optik - Int. J. Light Electron Opt. 127(19), 7762–7775 (2016)
Hui, Z.: An entropy-based objective evaluation method for image segmentation. Storage Retriev. Methods Appl. Multim., San Jose. 5307, 38–49 (2004)
Narwaria, M., Mantiuk, R.K., Silva, M., et al.: Hdr-vdp-2.2: a calibrated method for objective quality prediction of high-dynamic range and standard images. J. Electron Imag. 24(1), 010501 (2014)
Acknowledgements
The work described in this paper was partially supported by the National Natural Science Foundation of China (61772432, 61503309).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xia, S., Guo, S., Qu, Z. et al. A coarse-to-fine ghost removal scheme for HDR imaging. Vis Comput 39, 2515–2528 (2023). https://doi.org/10.1007/s00371-022-02475-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-022-02475-5