Owing to the limitation of dynamic range, a single still image is usually insufficient to describe a high contrast scene. Fusing multi-exposure images of the same scene can produce a resulting image with details both in the bright and the dark regions. However, they may be sensitive to the exposure parameters of the input images. In this study, a global layer is introduced to improve the robustness of the fusion method. The global layer is employed to preserve the overall luminance of a real scene and avoid possible luminance reversion artefacts. Then, details are recovered in the gradient domain by a Poisson solver. Experimental results show the superior performance of our approach in terms of robustness and details preservation.

References

1. 1)
  - 22. Pham, T.Q., van Vliet, L.J.: ‘Separable bilateral filtering for fast video preprocessing’. Int. Conf. on Multimedia and Expo (ICME 2005), Amsterdam, The Netherlands, 2005.
2. 2)
  - 10. Yang, Q.X.: ‘Recursive bilateral filtering’. European Conf. on Computer Vision 2012 (EVVC 2012), Firenze, Italy, 2012, pp. 399–413.
3. 3)
  - 17. Liu, L.X., Wang, Y.Q.: ‘A mean-edge structural similarity for Image quality’. Conf. Assessment Sixth Int. Conf. on Fuzzy Systems and Knowledge Discovery, Tianjin, China, 2009, pp. 311–315.
4. 4)
  - 4. Jo, K., Vavilin, A.: ‘HDR image generation based on intensity clustering and local feature analysis’, Comput. Hum. Behav., 2011, 27, (5), pp. 1507–1511 (doi: 10.1016/j.chb.2010.10.015).
5. 5)
  - 5. Shen, R., Cheng, I., Shi, J., Basu, A.: ‘Generalized random walks for fusion of multi-exposure images’, IEEE Trans. Image Process., 2011, 20, (12), pp. 3634–3646 (doi: 10.1109/TIP.2011.2150235).
6. 6)
  - 16. Zhang, W., Cham, W.: ‘Gradient-directed multiexposure composition’, IEEE Trans. Image Process., 2012, 21, (4), pp. 2318–2323 (doi: 10.1109/TIP.2011.2170079).
7. 7)
  - 19. Wang, Z., Bovik, A.C., Lu, L.G.: ‘Why is image quality assessment so difficult?’. Speech and Signal Processing, USA, 2009, pp. 3313–3316.
8. 8)
  - 24. Durand, F., Dorsey, J.: ‘Fast bilateral filtering for the display of high-dynamic-range images’, ACM Trans. Graph., 2002, 21, (3), pp. 257–266 (doi: 10.1145/566654.566574).
9. 9)
  - 7. Agrawal, A., Chellappa, R., Raskar, R.: ‘An algebraic approach to surface reconstruction from gradient fields’. 10th IEEE Int. Conf. on Computer Vision, Beijing, China, 2005, pp. 174–181.
10. 10)
  - 12. Duan, J., Bressan, M., Dance, C., Qiu, G.: ‘Tone-mapping high dynamic range images by novel histogram adjustment’, Pattern Recognit., 2010, 43, (5), pp. 1847–1862 (doi: 10.1016/j.patcog.2009.12.006).
11. 11)
  - 9. Perez, P.: ‘Poisson image editing’. Proc. ACM SIGGRAPH, San Diego, CA, 2003, pp. 313–318.
12. 12)
  - 21. Paris, S., Kornprobst, P., Tumblin, J., Durand, F., et al: ‘Bilateral filtering: theory and applications’, Found. Trends Comput. Graph. Vis., 2009, 4, (1), pp. 1–73 (doi: 10.1561/0600000020).
13. 13)
  - 11. Reinhard, E., Ward, G., Pattanaik, S., Debevec, P.: ‘High dynamic range imaging: acquisition, display and image-based lighting’ (Elsevier Inc., 2006).
14. 14)
  - 13. Press, W.H., Teukolsk, S.A., Vetterling, W.T., Flannery, B.P.: ‘Numerical recipes in C: the art of scientific computing’ (Cambridge Univ. Press, New York, 1992).
15. 15)
  - 15. HDRShop V1: http://www.hdrshop.com/.
16. 16)
  - 18. Yang, B., Lei, L., Yang, J.L.: ‘HVS-based structural image quality assessment model’. Conf. on Intelligent Control and Automation, Chongqing, China, 2008, pp. 8497–8500.
17. 17)
  - 23. Weiss, B.: ‘Fast median and bilateral filtering’, ACM Trans. Graph., Proc. ACM SIGGRAPH Conf., 2006, 25, (3), pp. 519–526 (doi: 10.1145/1141911.1141918).
18. 18)
  - 1. Mertens, T., Kautz, J., Van Reeth, F.: ‘Exposure fusion’. IEEE Conf. on 15th Pacific Computer Graphics and Applications, Washington, DC, USA, 2007, pp. 382–390.
19. 19)
  - 8. Agrawal, A., Raskar, R., Chellappa, R.: ‘What is the range of surface reconstructions from a gradient field?’. European Conf. on Computer Vision 2006 (ECCV 2006), Graz, Austria, 2006, pp. 578–591.
20. 20)
  - 6. Song, M., Tao, D., Chen, C., et al: ‘Probabilistic exposure fusion’, IEEE Trans. Image Process., 2012, 21, (1), pp. 341–357 (doi: 10.1109/TIP.2011.2157514).
21. 21)
  - 25. Paris, S., Durand, F.: ‘A fast approximation of the bilateral filter using a signal processing approach’, Int. J. Comput. Vis., 2009, 81, (1), pp. 24–52 (doi: 10.1007/s11263-007-0110-8).
22. 22)
  - 20. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: ‘Image utility assessment: from error measurement to structural similarity’, IEEE Trans. Image Process., 2004, 13, (4), pp. 600–612 (doi: 10.1109/TIP.2003.819861).
23. 23)
  - 3. Várkonyi-Kóczy, A.R., Rovid, A., Hashimoto, T.: ‘Gradient-based synthesized multiple exposure time color HDR image’, IEEE Trans. Instrum. Meas., 2008, 57, (8), pp. 1779–1785 (doi: 10.1109/TIM.2008.925715).
24. 24)
  - 14. Li, X.G., Lam, K.M., Shen, L.: ‘An adaptive algorithm for the display of high-dynamic range images’, J. Vis. Commun. Image Represent., 2007, 18, (5), pp. 397–405 (doi: 10.1016/j.jvcir.2007.06.005).
25. 25)
  - 2. Vavilin, A., Deb, K., Jo, K.: ‘Fast HDR image generation technique based on exposure blending’. IEA/AIE'10. Part III. LNAI6098, Berlin, Heidelberg, 2010, pp. 379–388.

Layered-based exposure fusion algorithm

References

Related content