Abstract

Exposure fusion (EF) directly generates a low dynamic range (LDR) image with similar image quality to the high dynamic range (HDR) image by combining images of different exposures to overcome the limited dynamic range of common digital cameras. EF for dynamic scenes is challenging not only due to the difficulty in removing various ghost artifacts but also because of the requirement of preserving details, especially in the saturated regions. Recently, low-rank (LR) matrix completion (LRMC) has been shown to be efficient in separating the latent background from the sparse motion in the irradiance domain. However, the performance of LRMC models strongly relies on the estimated irradiance images. To address this problem, this paper proposes a novel EF method combining Retinex theory and the LRMC model. The proposed method consists of four steps. First, according to Retinex theory, an image is decomposed into illumination and reflection components. Second, the LRMC model is applied to the reflection component to generate the background reflection component and the sparse error. Third, the motion map is modeled as a Markov random field (MRF), integrating the sparse error with the ordering constraint across all the illumination components. Finally, all the illumination components are fused via a pyramid-based method, where the weight maps are defined based on the obtained motion map and illumination. The experimental results show that the proposed method outperforms the state-of-the-art methods particularly in preserving details in saturated regions.

Highlights

  • Conventional digital cameras capture a small range of luminance levels, which does not include all of those in real-world scenes

  • In this paper, a new Exposure fusion (EF) method combining Retinex theory and LR matrix completion (LRMC) is proposed for dynamic scenes

  • In contrast to previous LRMC-based High dynamic range (HDR) imaging methods, the proposed method works in the intensity domain so that the exposure parameters and the camera response function (CRF) are not needed

Read more

Summary

Introduction

Conventional digital cameras capture a small range of luminance levels, which does not include all of those in real-world scenes. Many software techniques have been proposed to generate an HDR or HDR-like low dynamic range (LDR) image from a single image or from multiple images. The former is mainly intended to enhance details in low-light regions [4]–[6], in which the input LDR image exhibits only. Some methods achieve spectacular results [7], [8] when the scene is absolutely static but inevitably produce ghost artifacts if movement occurs in the scene To overcome this challenge, numerous techniques for removing ghost artifacts [9]–[11] have been proposed

Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.