An optimization framework for inverse tone mapping using a single low dynamic range image
| Autor: | Ming Fan, Sung-Jea Ko, Dae Hong Lee, Seung Wook Kim |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Low dynamic range
Computer science media_common.quotation_subject ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Inverse 02 engineering and technology Tone mapping GeneralLiterature_MISCELLANEOUS Image (mathematics) symbols.namesake 0202 electrical engineering electronic engineering information engineering Contrast (vision) Computer vision Electrical and Electronic Engineering Newton's method High dynamic range ComputingMethodologies_COMPUTERGRAPHICS media_common business.industry 020206 networking & telecommunications Function (mathematics) Signal Processing symbols 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business Software |
| Zdroj: | Signal Processing: Image Communication. 78:274-283 |
| ISSN: | 0923-5965 |
| DOI: | 10.1016/j.image.2019.07.009 |
| Popis: | Conventional inverse tone-mapping (ITM) methods tend to produce contrast distortions such as contrast loss and contrast reversal in reconstructed high dynamic range (HDR) images. This paper proposes a novel ITM optimization framework based on the assumption that the input low dynamic range (LDR) image is similar to the LDR image obtained by tone mapping a true HDR image. In the proposed framework, an HDR image is initially reconstructed by applying a conventional tone-mapping function in a reverse manner, and then the reconstructed HDR image is iteratively modified toward the optimum HDR image by minimizing the difference between the input LDR image and a tone-mapped LDR image obtained from the reconstructed HDR image. The experimental results demonstrate that the proposed framework effectively reconstructs a high-quality HDR image and outperforms other conventional methods in terms of objective quality. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect