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
Proceedings ArticleDOI
TL;DR: An enhanced IMSR method in a device-independent color space, CIELAB, to preserve hue and obtain high contrast and naturalness is proposed, and visibility in dark shadow and bright regions was improved and color distortion was reduced.
Abstract: Recently, tone reproduction is widely used in the field of image enhancement and HDR imaging This method is especially used to provide the proper luminance so that captured images give the same sensation as the scene As a result, we can get high contrast and naturalness of colors There is ample literature on the topic of tone reproduction that has the objective of reproducing natural looking color in digital images In recent papers, IMSR (Integrated multi-scale Retinex) shows great naturalness in the result images Most methods, including IMSR, work in RGB or quasi-RGB color spaces, although some method adopted the use of luminance This raises hue distortion from the point of the human visual system, that is, hue distortion in CIELAB color space Accordingly, this paper proposes an enhanced IMSR method in a device-independent color space, CIELAB, to preserve hue and obtain high contrast and naturalness In order to achieve the devised objectives, a captured sRGB image is transformed to the CIELAB color space IMSR is then applied to only L* values, thus the balance of colors components are preserved This process causes unnatural saturation, therefore saturation adjustment is performed by applying the ratio of chroma variation at the sRGB gamut boundary according to the corrected luminance Finally, the adjusted CIELAB values are transformed to sRGB using the inverse transform function In the result images of the proposed method, containing both high and low luminance regions, visibility in dark shadow and bright regions was improved and color distortion was reduced

3 citations

Proceedings ArticleDOI
Haesoo Chung1, Yoonsik Kim1, Junho Jo1, Sang-Hoon Lee1, Nam Ik Cho1 
01 Nov 2019
TL;DR: The proposed framework is an end-to-end trainable method without any preprocessing, which not only avoids ghosting or blurring artifacts but also hallucinates fine details effectively.
Abstract: Generating a high dynamic range (HDR) image from multiple exposure images is challenging in the presence of significant motions, which usually causes ghosting artifacts. To alleviate this problem, previous methods explicitly align the input images before merging the controlled exposure images. Although recent works try to learn the HDR imaging process using a convolutional neural network (CNN), they still suffer from ghosting or blurring artifacts and missing details in extremely under/overexposed areas. In this paper, we propose an end-to-end framework for detail-preserving HDR imaging of dynamic scenes. Our method employs a kernel prediction network and produces per-pixel kernels to fully utilize every pixel and its neighborhood in input images for the successful alignment. After applying the kernels to the input images, we generate a final HDR image using a simple merging network. The proposed framework is an end-to-end trainable method without any preprocessing, which not only avoids ghosting or blurring artifacts but also hallucinates fine details effectively. We demonstrate that our method provides comparable results to the state-of-the-art methods regarding qualitative and quantitative evaluations.

3 citations

Proceedings ArticleDOI
TL;DR: The paper describes the Near Sensor Image Processing (NSIP) paradigm and shows that it was a precursor to recent architectures proposed for direct (in the sensor) image processing and high dynamic range (HDR) image sensing.
Abstract: The paper describes the Near Sensor Image Processing (NSIP) paradigm developed in the early 1990s and shows that it was a precursor to recent architectures proposed for direct (in the sensor) image processing and high dynamic range (HDR) image sensing. Both of these architectures are based on the specific properties of CMOS light sensors, in particular the ability to continuously monitor the accumulation of photon-induced charge as a function of time. We further propose an extension of the original NSIP pixel to include a circuit that facilitates temporal and spatio-temporal processing.

3 citations

01 Jan 2009
TL;DR: A comprehensive overview on HDR Imaging, and an in depth review on these emerging topics, proposing how to classify and to validate them and limits of these methods are discussed, showing the remaining challenges for the future.
Abstract: In the last few years researches in the High Dynamic Range (HDR) Imaging field have focused on providing tools for expanding LDR content for the generation of HDR images and videos for HDR displays and Image Based Lighting. Furthermore, another important problem has been tackled, the space compression of HDR content using a tone mapping operator (TMOs) and its inverse. The goal of this report is to provide a comprehensive overview on HDR Imaging, and an in depth review on these emerging topics. Moreover, we are proposing how to classify and to validate them. Furthermore, limits of these methods are discussed, showing the remaining challenges for the future.

3 citations

Proceedings ArticleDOI
10 Dec 2015
TL;DR: The estimation of the HDR image from a set of LDR images is formulated as a stochastically fully connected conditional random field where the spatial information is incorporated to compute the HDR value in combination with the LDR image values.
Abstract: The reconstruction of high dynamic range (HDR) images via conventional camera systems and low dynamic range (LDR) images is a growing field of research in image acquisition. The radiance map associated with the HDR image of a scene is typically computed using multiple images of the same scene captured at different exposures (i.e., bracketed LDR imzages). This approach, though inexpensive, is sensitive to noise under high camera ISO. Each bracketed image is associated with a different level of noise due to the change in exposure time, and the noise is further amplified when tone-mapping the HDR image for display. A new framework is proposed to address the associated noise in the context of random fields. The estimation of the HDR image from a set of LDR images is formulated as a stochastically fully connected conditional random field where the spatial information is incorporated to compute the HDR value in combination with the LDR image values. Experimental results show that the proposed framework compensated the non-stationary ISO noise while preserving the boundaries in the estimated HDR images.

3 citations


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