Single Image Brightening via Multi-Scale Exposure Fusion With Hybrid Learning

Zheng, Chaobing; Li, Zhengguo; Yang, Yi; Wu, Shiqian

doi:10.1109/tcsvt.2020.3009235

Cited by 48 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimization to the guided image filtering technique was performed by incorporating an edge-aware weighting into the guided filter, which greatly reduced the halo artifacts in images. 19 Zheng et al 20 proposed to create a hybrid model that consists of both a model-driven and data-driven approach to generate a higher quality image. In this paper, we have mainly focused on the data-driven approach via the use of cGAN.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

Adversarial and adaptive tone mapping operator: multi-scheme generation and multi-metric evaluation

et al. 2021

View full text Add to dashboard Cite

Tone mapping is one of the main techniques to convert high-dynamic range (HDR) images into low-dynamic range (LDR) images. We propose to use a variant of generative adversarial networks to adaptively tone map images. We designed a conditional adversarial generative network composed of a U-Net generator and patchGAN discriminator to adaptively convert HDR images into LDR images. We extended previous work to include additional metrics such as tone-mapped image quality index (TMQI), structural similarity index measure, Fréchet inception distance, and perceptual path length. In addition, we applied face detection on the Kalantari dataset and showed that our proposed adversarial tone mapping operator generates the best LDR image for the detection of faces. One of our training schemes, trained via 256 × 256 resolution HDR-LDR image pairs, results in a model that can generate high TMQI low-resolution 256 × 256 and high-resolution 1024 × 2048 LDR images. Given 1024 × 2048 resolution HDR images, the TMQI of the generated LDR images reaches a value of 0.90, which outperforms all other contemporary tone mapping operators. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Section: Generative Adversarial Networkmentioning

confidence: 99%

Adversarial and adaptive tone mapping operator: multi-scheme generation and multi-metric evaluation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…K EYPOINTS matching is an essential module in many image processing problems such as the visual SLAM, image stitching, and so on. It aims to establish 2D-2D matches (correspondences) of keypoints [1]- [4] between two images, so that the relative pose of cameras can be recovered with the multi-view geometry [5], [6] or a set of differently exposed images [7], [8]. Therefore, it becomes important to restore as many correct matches as possible.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network

Zhao

Liu

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Keypoints matching is a pivotal component for many image-relevant applications such as image stitching, visual simultaneous localization and mapping (SLAM), and so on. Both handcrafted-based and recently emerged deep learning-based keypoints matching methods merely rely on keypoints and local features, while losing sight of other available sensors such as inertial measurement unit (IMU) in the above applications. In this paper, we demonstrate that the motion estimation from IMU integration can be used to exploit the spatial distribution prior of keypoints between images. To this end, a probabilistic perspective of attention formulation is proposed to integrate the spatial distribution prior into the attentional graph neural network naturally. With the assistance of spatial distribution prior, the effort of the network for modeling the hidden features can be reduced. Furthermore, we present a projection loss for the proposed keypoints matching network, which gives a smooth edge between matching and un-matching keypoints. Image matching experiments on visual SLAM datasets indicate the effectiveness and efficiency of the presented method.

show abstract

“…In this paper, the saturation is restored by fusing datadriven and model-based approaches rather than the data-driven approaches in [17], [18]. As indicated in [19], such a neural augmentation must posses the complete domain knowledge it requires as in [20]. The camera response functions (CRFs) are thus assumed to be known in advance.…”

Section: Introductionmentioning

confidence: 99%

“…Otherwise, the fixed ratio strategy in [3] is applied to reduce the color distortion. The generation of the initial dark image is focused on because the generation of the initial brighter image has been studied in [20]. The initially synthetic images are refined by a novel exposedness aware saturation restoration network (EASRN) which is proposed by incorporating an exposedness aware guidance branch (EAGB) into a nonlocal recursive residual group (NRRG).…”

Section: Introductionmentioning

confidence: 99%

“…The initially synthetic images are refined by a novel exposedness aware saturation restoration network (EASRN) which is proposed by incorporating an exposedness aware guidance branch (EAGB) into a nonlocal recursive residual group (NRRG). As pointed out in [20], the objective of [20] is to explore the feasibility of the neural augmentation framework rather than a sophisticated deep neural network (DNN) for single image brightening. The DNN in [20] is a ResNet [21] with multiple residual blocks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Saturation Restoration for LDR Images of HDR Scenes

Zheng¹,

Li²,

Wu³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

There are shadow and highlight regions in a low dynamic range (LDR) image which is captured from a high dynamic range (HDR) scene. It is an ill-posed problem to restore the saturated regions of the LDR image. In this paper, the saturated regions of the LDR image are restored by fusing model-based and data-driven approaches. With such a neural augmentation, two synthetic LDR images are first generated from the underlying LDR image via the model-based approach. One is brighter than the input image to restore the shadow regions and the other is darker than the input image to restore the high-light regions. Both synthetic images are then refined via a novel exposedness aware saturation restoration network (EASRN). Finally, the two synthetic images and the input image are combined together via an HDR synthesis algorithm or a multi-scale exposure fusion algorithm. The proposed algorithm can be embedded in any smart phones or digital cameras to produce an information-enriched LDR image.

show abstract

Single Image Brightening via Multi-Scale Exposure Fusion With Hybrid Learning

Cited by 48 publications

References 37 publications

Adversarial and adaptive tone mapping operator: multi-scheme generation and multi-metric evaluation

Adversarial and adaptive tone mapping operator: multi-scheme generation and multi-metric evaluation

Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network

Hybrid Saturation Restoration for LDR Images of HDR Scenes

Contact Info

Product

Resources

About