Ghost-Free High Dynamic Range Imaging

Abstract

We propose a ghost-free high dynamic range (HDR) image synthesis algorithm using a low-rank matrix completion framework, which we call RM-HDR. Based on the assumption that irradiance maps are linearly related to low dynamic range (LDR) image exposures, we formulate ghost region detection as a rank minimization problem. We incorporate constraints on moving objects, i.e., sparsity, connectivity, and priors on under and over exposed regions into the framework. Experiments on real image collections shows that the RM-HDR can often provide significant gains in synthesized HDR image quality over state-of-the-art approaches. Additionally, a complexity analysis is performed which reveals computational merits of RM-HDR over recent advances in deghosting for HDR.

Results


SculptureGarden [2]

Debevec and Malik [1] Gallo et al. [2]
Heo et al. [3] Hu et al. [4]
Oh et al. [5] Zheng et al. [6]
Zhang et al. [7] Mertens et al. [8]
Proposed



Arch [2]

Debevec and Malik [1] Gallo et al. [2]
Heo et al. [3] Hu et al. [4]
Oh et al. [5] Zheng et al. [6]
Zhang et al. [7] Mertens et al. [8]
Proposed

References

  1. P. Debevec and J. Malik, “Recovering high dynamic range radiance maps from photographs,” in Proc. SIGGRAPH 97, Aug. 1997, pp. 369-378.

  2. O. Gallo, N. Gelfand, W.-C. Chen, M. Tico, and K. Pulli, “Artifact-free high dynamic range imaging,” in Proc. IEEE ICCP, Apr. 2009, pp. 1–7.

  3. Y. S. Heo, K. M. Lee, S. U. Lee, Y. Moon, and J. Cha, “Ghost-free high dynamic range imaging,” in Proc. ACCV, Nov. 2010, pp. 486–500.

  4. J. Hu, O. Gallo, K. Pulli, and X. Sun, “HDR deghosting: How to deal with saturation?” in Proc. IEEE CVPR, Jun. 2013, pp. 1163–1170.

  5. T.-H. Oh, J.-Y. Lee, and I. S. Kweon, “High dynamic range imaging by a rank-1 constraint,” in Proc. IEEE ICIP, Sep. 2013, pp. 790–794.

  6. J. Zheng, Z. Li, Z. Zhu, S. Wu, and S. Rahardja, “Hybrid patching for a sequence of differently exposed images with moving objects,” IEEE Trans. Image Process., vol. 22, no. 12, pp. 5190–5201, Dec. 2013.

  7. W. Zhang and W.-K. Cham, “Gradient-directed multiexposure composition,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 2318–2323, Apr. 2012.

  8. T. Mertens, J. Kautz, and F. V. Reeth, “Exposure fusion: A simple and practical alternative to high dynamic range photography,” Computer Graphics Forum, vol. 28, no. 1, pp. 161–171, Mar. 2009.

Publication

Code