Multi-Exposure Decomposition-Fusion Model for High Dynamic Range Image Saliency Detection

Wang, Xu; Sun, Zhenhao; Zhang, Qiudan; Fang, Yuming; Ma, Lin; Wang, Shiqi

doi:10.1109/tcsvt.2020.2985427

Cited by 18 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiment, we employ seven state-of-the-art saliency prediction methods for comprehensive comparisons. The involved methods include four learning based saliency prediction methods for LDR images (MLNet [11], SALICON [10], GAZEGAN [12] and SAM-VGG [8]), a traditional saliency prediction method (Dong et al's method [13]) and two learning based methods (LBVS-HDR [14] and DF-HSal [25]) for HDR images. In addition, we use the source codes of the involved methods and their provided models for performance evaluation.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

“…There are a few studies [3,[23][24][25] that focus on saliency prediction of HDR images. For instance, Brémond et al [23] proposed a saliency method derived from Itti et al's method [15] to detect HDR image saliency by introducing contrast feature in the feature extraction phrase.…”

Section: Saliency Prediction For Hdr Imagesmentioning

confidence: 99%

“…However, the conventional hand-crafted features incorporated in the above methods greatly limit the performance of saliency prediction owing to the absence of high-level semantic information. Recently, inspired by the brightness adaptation mechanism, Wang et al [25] designed a multiexposure decomposition-fusion saliency detection model for HDR images. While this model consists of three independent modules that leads to higher computational complexity.…”

Section: Saliency Prediction For Hdr Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Multi‐exposure embeddings for graph learning: Towards high dynamic range image saliency prediction

Xing,

Zhang,

Shen

et al. 2024

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Identifying saliency in high dynamic range (HDR) images is a fundamentally important issue in HDR imaging, and plays critical roles towards comprehensive scene understanding. Most of existing studies leverage hand‐crafted features for HDR image saliency prediction, lacking the capabilities of fully exploiting the characteristics of HDR image (i.e. wider luminance range and richer colour gamut). Here, systematical studies are carried out on HDR image saliency prediction by proposing a new framework to single out the contributions from multi‐exposure images. Specifically, inspired by the mechanism of HDR imaging, the method first utilizes graph neural networks to model the relations among multi‐exposure images and the tone‐mapped image obtained from an HDR image, enabling more discriminative saliency‐related feature representations. Subsequently, the saliency features driven by global semantic knowledge are aggregated from the tone‐mapped image through enhancing global context‐aware semantic information. Finally, a fusion module is designed to integrate saliency‐oriented feature representations originated from multi‐exposure images and the tone‐mapped image, producing the saliency maps of HDR images. Moreover, a new challenging HDR eye fixation database (HDR‐EYEFix) is created, expecting to further contribute the research on HDR image saliency prediction. Experiment results show that the method obtains superior performance compared to the state‐of‐the‐art methods.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Section: Saliency Prediction For Hdr Imagesmentioning

confidence: 99%

Section: Saliency Prediction For Hdr Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐exposure embeddings for graph learning: Towards high dynamic range image saliency prediction

Xing,

Zhang,

Shen

et al. 2024

IET Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Existing DNN models use mapped LDR images to extract relevant features for object detection. [176] introduced a DNN-based framework for saliency detection of HDR content. The framework follows a similar idea as [28]: first, HDR images are transformed to LDR images; next, neural networks detect the salient regions.…”

Section: Applicationsmentioning

confidence: 99%

Deep Learning for HDR Imaging: State-of-the-Art and Future Trends

Wang

Yoon

2021

Preprint

View full text Add to dashboard Cite

High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imaging using deep learning (DL). This study conducts a comprehensive and insightful survey and analysis of recent developments in deep HDR imaging methodologies. We hierarchically and structurally group existing deep HDR imaging methods into five categories based on (1) number/domain of input exposures, (2) number of learning tasks, (3) novel sensor data, (4) novel learning strategies, and (5) applications. Importantly, we provide a constructive discussion on each category regarding its potential and challenges. Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.

show abstract

“…The main difference between these image fusion tasks is that the source images are different, and the source images of MEF are a series of images with different exposure levels. In addition, it can also be used for image enhancement under low illumination [6,7], defogging [8], and saliency detection [9] by fusing or generating pseudo exposure sequences.…”

Section: Introductionmentioning

confidence: 99%

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Liu

Song

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Multi-exposure image fusion (MEF) is emerging as a research hotspot in the fields of image processing and computer vision, which can integrate images with multiple exposure levels into a full exposure image of high quality. It is an economical and effective way to improve the dynamic range of the imaging system and has broad application prospects. In recent years, with the further development of image representation theories such as multi-scale analysis and deep learning, significant progress has been achieved in this field. This paper comprehensively investigates the current research status of MEF methods. The relevant theories and key technologies for constructing MEF models are analyzed and categorized. The representative MEF methods in each category are introduced and summarized. Then, based on the multi-exposure image sequences in static and dynamic scenes, we present a comparative study for 18 representative MEF approaches using nine commonly used objective fusion metrics. Finally, the key issues of current MEF research are discussed, and a development trend for future research is put forward.

show abstract

Multi-Exposure Decomposition-Fusion Model for High Dynamic Range Image Saliency Detection

Cited by 18 publications

References 30 publications

Multi‐exposure embeddings for graph learning: Towards high dynamic range image saliency prediction

Multi‐exposure embeddings for graph learning: Towards high dynamic range image saliency prediction

Deep Learning for HDR Imaging: State-of-the-Art and Future Trends

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Contact Info

Product

Resources

About