Pseudo-Multiple-Exposure-Based Tone Fusion With Local Region Adjustment

Wang, Tsun-Hsien; Chiu, Cheng-Wen; Wu, Wei-Chen; Wang, Jen-Wen; Lin, Chun-Yi; Chiu, Ching-Te; Liou, Jing-Jia

doi:10.1109/tmm.2015.2403612

Cited by 79 publications

(48 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generating an HDR image from a single exposure image is called a single image HDR in some software tools or reverse tone mapping [21,[42][43][44][45]. The reverse tone mapping operation (rTMO) is an ill-posed problem because it tries to find the information that was lost during the capturing process.…”

Section: Hdr Image Generation and Applications 1) Extension To Thementioning

confidence: 99%

“…In this subsection, we test whether the pseudo multi-exposures generated by our algorithm can be used for generating an HDR image, i.e., we test the feasibility of our method for rTMO. For this, we generate some of the HDR images by the reverse tone mapping functions provided in the HDR Matlab toolbox [45] and also provided by the author in [21].…”

Section: Hdr Image Generation and Applications 1) Extension To Thementioning

confidence: 99%

See 1 more Smart Citation

Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images

Park

Soh

Cho

2019

Multimed Tools Appl

View full text Add to dashboard Cite

This paper presents an algorithm that enhances undesirably illuminated images by generating and fusing multi-level illuminations from a single image. The input image is first decomposed into illumination and reflectance components by using an edge-preserving smoothing filter. Then the reflectance component is scaled up to improve the image details in bright areas. The illumination component is scaled up and down to generate several illumination images that correspond to certain camera exposure values different from the original. The virtual multi-exposure illuminations are blended into an enhanced illumination, where we also propose a method to generate appropriate weight maps for the tone fusion. Finally, an enhanced image is obtained by multiplying the equalized illumination and enhanced reflectance. Experiments show that the proposed algorithm produces visually pleasing output and also yields comparable objective results to the conventional enhancement methods, while requiring modest computational loads.

show abstract

Section: Hdr Image Generation and Applications 1) Extension To Thementioning

confidence: 99%

Section: Hdr Image Generation and Applications 1) Extension To Thementioning

confidence: 99%

Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images

Park

Soh

Cho

2019

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…For generating an HDR image from a single input, most of the conventional methods generate the virtual multiexposure images by applying brightness enhancement functions and then fuse them with the appropriate weight maps obtained from each of the virtual images [49,53,8,14,19,24,40]. Among these techniques, the Retinex based approaches [8,14,19,24,40] enhance the illumination and reflectance components separately.…”

Section: High Dynamic Range Imaging From a Single Imagementioning

confidence: 99%

Joint High Dynamic Range Imaging and Super-Resolution From a Single Image

2019

View full text Add to dashboard Cite

This paper presents a new framework for jointly enhancing the resolution and the dynamic range of an image, i.e., simultaneous super-resolution (SR) and high dynamic range imaging (HDRI), based on a convolutional neural network (CNN). From the common trends of both tasks, we train a CNN for the joint HDRI and SR by focusing on the reconstruction of high-frequency details. Specifically, the high-frequency component in our work is the reflectance component according to the Retinex-based image decomposition, and only the reflectance component is manipulated by the CNN while another component (illumination) is processed in a conventional way. In training the CNN, we devise an appropriate loss function that contributes to the naturalness quality of resulting images. Experiments show that our algorithm outperforms the cascade implementation of CNN-based SR and HDRI.

show abstract

“…From acquisition to display, several significant developments have been made in High Dynamic Range (HDR) imagery in the last couple of decades [3]. It has been successfully applied to several multimedia technologies, including video coding [4], inverse tone mapping [5], saliency detection [6], data hiding [7], and quality assessment [8], but also to fields such as automotive or spacecrafts imaging [9]. HDR enables to capture a wider dynamic range and color gamut, encapsulating a vast amount of information.…”

Section: Introductionmentioning

confidence: 99%

Learning-Based Tone Mapping Operator for Efficient Image Matching

Rana

Valenzise

Dufaux

2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

To cite this version:Aakanksha Rana, Giuseppe Valenzise, Frédéric Dufaux. Learning-based tone mapping operator for efficient image matching.Abstract-In this paper, we propose a new framework to optimally tone map the high dynamic range (HDR) content for image matching under drastic illumination variations. Since tone mapping operators (TMO) have traditionally been used for displaying HDR scenes, their design is suboptimal when used for computer vision tasks such as image matching. We address this sub-optimality by proposing a two-step framework, consisting of: a) a luminance-invariant guidance model based on a Support Vector Regressor (SVR) to optimally adapt the tone mapping function for image matching; and b) an energy maximization model to generate appropriate training samples for learning the SVR. At each step, we collectively address both stages of keypoint detection and descriptor extraction in the feature matching framework. By locally altering the intrinsic characteristics of the tone mapping function, the learned guidance model facilitates the extraction of local invariant features in the presence of illumination variations. We demonstrate that the proposed TMO significantly outperforms perceptually-driven state-of-the-art TMOs on a dataset of HDR scenes characterized by challenging lighting variations, such as day/night transitions.Index Terms-High dynamic range, tone mapping operator, image matching, stochastic gradient descent, machine learning.

show abstract

Pseudo-Multiple-Exposure-Based Tone Fusion With Local Region Adjustment

Cited by 79 publications

References 29 publications

Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images

Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images

Joint High Dynamic Range Imaging and Super-Resolution From a Single Image

Learning-Based Tone Mapping Operator for Efficient Image Matching

Contact Info

Product

Resources

About