Learning Stereo High Dynamic Range Imaging From A Pair of Cameras With Different Exposure Parameters

Chen, Yeyao; Jiang, Gangyi; Yu, Mei; You, Yang; Ho, Yo‐Sung

doi:10.1109/tci.2020.3001398

Cited by 19 publications

(13 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks with a deep structure have been widely proved to have strong feature representation ability and are very useful for various image and vision tasks, including image fusion. Currently, deep learning models, including convolutional neural networks (CNNs) [16] and generative adversarial networks (GANs) [17], have been successfully applied to MEF. Depending on the model employed, deep learning-based methods can be further classified into supervised-based and unsupervised-based methods.…”

Section: A Review On Mefmentioning

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

Section: A Review On Mefmentioning

confidence: 99%

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Liu

Song

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The LDR camera usually sets an appropriate exposure time ∆t and relies on the camera response function (CRF) f CRF to map the irradiance E of scenes to the LDR image x [32].…”

Section: Problem Datasets and Evaluation 21 Definition Of Deep Hdr Im...mentioning

confidence: 99%

“…2(a) aims to create an HDR content by learning from multi-exposure LDR images with DNNs [9], [33]. Specifically, multi-exposure LDR images can be mapped to the irradiance domain using DNNs based on the inverse CRF and exposure time (∆t) (or exposure value (EV) [32]) from Eq. (1) and Eq.…”

Section: Problem Datasets and Evaluation 21 Definition Of Deep Hdr Im...mentioning

confidence: 99%

“…2(b), where an inverse tonemapping network is learned to generate an HDR image reflecting natural illumination. However, as a single-exposure LDR image conveys limited exposure information, learning the HDR visual content from it is an ill-posed problem [3], [32]. Therefore, the reconstructed HDR image has a limited dynamic range, which indicates that the visual quality of the HDR images is inferior to that of the multiple-exposure LDR images.…”

Section: Problem Datasets and Evaluation 21 Definition Of Deep Hdr Im...mentioning

confidence: 99%

“…Thus, HDR LV and RV image pairs are obtained. By contrast, the method in [32] follows the conventional pipeline of [99] and replaces it with three learning modules: an exposure calibration network, a hole-filling network, and an HDR fusion network. Consequently, the proposed method better addresses the challenges of distorted brightness and color attributes and detail loss in fused HDR images.…”

Section: Deep Stereo-based Hdr Imagingmentioning

confidence: 99%

See 2 more Smart Citations

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

A Novel Cross-Resolution Image Alignment for Multi-camera System

Chen

Zheng

et al. 2022

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Learning Stereo High Dynamic Range Imaging From A Pair of Cameras With Different Exposure Parameters

Cited by 19 publications

References 40 publications

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

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

A Novel Cross-Resolution Image Alignment for Multi-camera System

Contact Info

Product

Resources

About