scispace - formally typeset
Search or ask a question
Topic

High-dynamic-range imaging

About: High-dynamic-range imaging is a research topic. Over the lifetime, 766 publications have been published within this topic receiving 22577 citations.


Papers
More filters
Book ChapterDOI
01 Jan 2023
TL;DR: CEN-HDR as mentioned in this paper proposes a novel architecture based on a light attention mechanism and sub-pixel convolution operations for real-time HDR imaging, which provides competitive results in image quality while being faster than state-of-the-art solutions.
Abstract: High dynamic range (HDR) imaging is still a challenging task in modern digital photography. Recent research proposes solutions that provide high-quality acquisition but at the cost of a very large number of operations and a slow inference time that prevent the implementation of these solutions on lightweight real-time systems. In this paper, we propose CEN-HDR, a new computationally efficient neural network by providing a novel architecture based on a light attention mechanism and sub-pixel convolution operations for real-time HDR imaging. We also provide an efficient training scheme by applying network compression using knowledge distillation. We performed extensive qualitative and quantitative comparisons to show that our approach produces competitive results in image quality while being faster than state-of-the-art solutions, allowing it to be practically deployed under real-time constraints. Experimental results show our method obtains a score of 43.04 $$\mu $$ -PSNR on the Kalantari2017 dataset with a framerate of 33 FPS using a Macbook M1 NPU. The proposed network will be available at https://github.com/steven-tel/CEN-HDR
Patent
10 Aug 2009
TL;DR: In this article, an image processor detects the correlation of the plurality of shot images based on additional information or a pixel distribution thereof, and groups the shot images having the correlation as multistage exposure images to be displayed on the display part, whereby dynamic range expansion processing and gradation compression processing can be executed to an appropriate multi-age exposure image group and shot images reduced in over exposure under exposure and the like can be acquired.
Abstract: PROBLEM TO BE SOLVED: To appropriately select a multistage exposure image group for performing HDR (High Dynamic Range Imaging) processing. SOLUTION: In the case of auto bracket imaging, this image processor extracts multistage exposure images each having an identical bracket group number from a plurality of shot images, and groups the extracted multistage exposure images to be displayed on a display part. In the case of normal imaging, the image processor detects the correlation of the plurality of shot images based on additional information or a pixel distribution thereof, and groups the shot images having the correlation as multistage exposure images to be displayed on the display part, whereby dynamic range expansion processing and gradation compression processing can be executed to an appropriate multistage exposure image group, and shot images reduced in over exposure under exposure and the like can be acquired. COPYRIGHT: (C)2011,JPO&INPIT
Journal ArticleDOI
TL;DR: In this paper, a maximum aposteriori probability (MAP) based reconstruction of the HDR image using Gibb's prior to model the radiance map, with total variation (TV) as the prior to avoid unnecessary smoothing of radiance field.
Abstract: High dynamic range imaging aims at creating an image with a range of intensity variations larger than the range supported by a camera sensor. Most commonly used methods combine multiple exposure low dynamic range (LDR) images, to obtain the high dynamic range (HDR) image. Available methods typically neglect the noise term while finding appropriate weighting functions to estimate the camera response function as well as the radiance map. We look at the HDR imaging problem in a denoising frame work and aim at reconstructing a low noise radiance map from noisy low dynamic range images, which is tone mapped to get the LDR equivalent of the HDR image. We propose a maximum aposteriori probability (MAP) based reconstruction of the HDR image using Gibb’s prior to model the radiance map, with total variation (TV) as the prior to avoid unnecessary smoothing of the radiance field. To make the computation with TV prior efficient, we extend the majorize-minimize method of upper bounding the total variation by a quadratic function to our case which has a nonlinear term arising from the camera response function. A theoretical justification for doing radiance domain denoising as opposed to image domain denoising is also provided.
Posted Content
TL;DR: The first challenge on high-dynamic range (HDR) imaging was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021 as discussed by the authors.
Abstract: This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021. This manuscript focuses on the newly introduced dataset, the proposed methods and their results. The challenge aims at estimating a HDR image from one or multiple respective low-dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed by two tracks: In Track 1 only a single LDR image is provided as input, whereas in Track 2 three differently-exposed LDR images with inter-frame motion are available. In both tracks, the ultimate goal is to achieve the best objective HDR reconstruction in terms of PSNR with respect to a ground-truth image, evaluated both directly and with a canonical tonemapping operation.
Patent
29 Aug 2012
TL;DR: In this paper, a method of enlarging the dynamic range of a depth map by obtaining depth information from a composite image of a plurality of images captured at different luminance levels and / or over different sensor accumulation times is described.
Abstract: A method of enlarging the dynamic range of a depth map by obtaining depth information from a composite image of a plurality of images captured at different luminance levels and / or over different sensor accumulation times is described. In some embodiments, an initial image of the environment is captured when the environment is illuminated with light of a first luminous intensity. When the environment is illuminated with light having one or more different luminous intensities, one or more of the following images are subsequently captured. The one or more different luminances can be dynamically configured based on the pixel saturation associated with the previously captured image. An HDR imaging technique (high dynamic range imaging technique) may be applied to synthesize an initial image and one or more subsequent images into a composite image.

Network Information
Related Topics (5)
Pixel
136.5K papers, 1.5M citations
84% related
Image processing
229.9K papers, 3.5M citations
83% related
Object detection
46.1K papers, 1.3M citations
81% related
Convolutional neural network
74.7K papers, 2M citations
80% related
Image segmentation
79.6K papers, 1.8M citations
80% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202333
202260
202129
202034
201937
201837