Overview of High-Dynamic-Range Image Quality Assessment [PDF]
Journal of ImagingIn recent years, the High-Dynamic-Range (HDR) image has gained widespread popularity across various domains, such as the security, multimedia, and biomedical fields, owing to its ability to deliver an authentic visual experience.
Yue Liu +4 more
doaj +2 more sources
Multi-Frame Content-Aware Mapping Network for Standard-Dynamic-Range to High-Dynamic-Range Television Artifact Removal [PDF]
SensorsRecently, advancements in image sensor technology have paved the way for the proliferation of high-dynamic-range television (HDRTV). Consequently, there has been a surge in demand for the conversion of standard-dynamic-range television (SDRTV) to HDRTV ...
Zheng Wang, Gang He
doaj +2 more sources
Deep high dynamic range imaging of dynamic scenes [PDF]
ACM Transactions on Graphics, 2017 Nima Khademi Kalantari, Ravi Ramamoorthi
openalex +2 more sources
Ghost-free High Dynamic Range Imaging with Context-aware Transformer [PDF]
European Conference on Computer Vision, 2022 High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details. Restricted by the locality of the receptive field, existing CNN-based methods are typically prone to producing ghosting artifacts and intensity ...
Z. Liu +3 more
semanticscholar +1 more source
HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content [PDF]
arXiv.org, 2023 High-Dynamic-Range Visual-Difference-Predictor version 3, or HDR-VDP-3, is a visual metric that can fulfill several tasks, such as full-reference image/video quality assessment, prediction of visual differences between a pair of images, or prediction of ...
Rafał K. Mantiuk +2 more
semanticscholar +1 more source
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images [PDF]
Computer Vision and Pattern Recognition, 2021 Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these images have been processed by a ...
B. Mildenhall +4 more
semanticscholar +1 more source
High Dynamic Range Imaging with Context-aware Transformer [PDF]
IEEE International Joint Conference on Neural Network, 2023 Avoiding the introduction of ghosts when synthesising LDR images as high dynamic range (HDR) images is a challenging task. Convolutional neural networks (CNNs) are effective for HDR ghost removal in general, but are challenging to deal with the LDR ...
Fangfang Zhou, Dan Zhang, Zhengming Fu
semanticscholar +1 more source
HDR-NeRF: High Dynamic Range Neural Radiance Fields [PDF]
Computer Vision and Pattern Recognition, 2021 We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures.
Xin Huang +5 more
semanticscholar +1 more source
ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet. This problem comprises two intractable challenges of how to handle saturation and noise properly and ...
Zhen Liu +8 more
semanticscholar +1 more source
HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields [PDF]
European Conference on Computer Vision, 2022 We propose high dynamic range (HDR) radiance fields, HDR-Plenoxels, that learn a plenoptic function of 3D HDR radiance fields, geometry information, and varying camera settings inherent in 2D low dynamic range (LDR) images.
Kim Jun-Seong +3 more
semanticscholar +1 more source