Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image areas, in order to enable HDR reconstruction from a single exposure. We show that this problem is well-suited for deep learning algorithms, and propose a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values. To train the CNN we gather a large dataset of HDR images, which we augment by simulating sensor saturation for a range of cameras. To further boost robustness, we pre-train the CNN on a simulated HDR dataset created from a subset of the MIT Places database. We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situations, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response functions and post-processing. Furthermore, we compare to existing methods for HDR expansion, and show high quality results also for image based lighting. Finally, we evaluate the results in a subjective experiment performed on an HDR display. This shows that the reconstructed HDR images are visually convincing, with large improvements as compared to existing methods.Comment: 15 pages, 19 figures, Siggraph Asia 2017. Project webpage located at http://hdrv.org/hdrcnn/ where paper with high quality images is available, as well as supplementary material (document, images, video and source code
Figure 1: Image reproduced adaptively for low ambient light (dark room scenario -left) and high ambient light (sunlight scenario -right). The display adaptive tone mapping can account for screen reflections when generating images that optimize visible contrast. AbstractWe propose a tone mapping operator that can minimize visible contrast distortions for a range of output devices, ranging from e-paper to HDR displays. The operator weights contrast distortions according to their visibility predicted by the model of the human visual system. The distortions are minimized given a display model that enforces constraints on the solution. We show that the problem can be solved very efficiently by employing higher order image statistics and quadratic programming. Our tone mapping technique can adjust image or video content for optimum contrast visibility taking into account ambient illumination and display characteristics. We discuss the differences between our method and previous approaches to the tone mapping problem.
Many quality metrics take as input gamma corrected images and assume that pixel code values are scaled perceptually uniform. Although this is a valid assumption for darker displays operating in the luminance range typical for CRT displays (from 0.1 to 80 cd/m 2 ), it is no longer true for much brighter LCD displays (typically up to 500 cd/m 2 ), plasma displays (small regions up to 1000 cd/m 2 ) and HDR displays (up to 3000 cd/m 2 ). The distortions that are barely visible on dark displays become clearly noticeable when shown on much brighter displays. To estimate quality of images shown on bright displays, we propose a straightforward extension to the popular quality metrics, such as PSNR and SSIM, that makes them capable of handling all luminance levels visible to the human eye without altering their results for typical CRT display luminance levels. Such extended quality metrics can be used to estimate quality of high dynamic range (HDR) images as well as account for display brightness.
New imaging and rendering systems commonly use physically accurate lighting information in the form of highdynamic range (HDR) images and video. HDR images contain actual colorimetric or physical values, which can span 14 orders of magnitude, instead of 8-bit renderings, found in standard images. The additional precision and quality retained in HDR visual data is necessary to display images on advanced HDR display devices, capable of showing contrast of 50,000:1, as compared to the contrast of 700:1 for LCD displays. With the development of high-dynamic range visual techniques comes a need for an automatic visual quality assessment of the resulting images.In this paper we propose several modifications to the Visual Difference Predicator (VDP). The modifications improve the prediction of perceivable differences in the full visible range of luminance and under the adaptation conditions corresponding to real scene observation. The proposed metric takes into account the aspects of high contrast vision, like scattering of the light in the optics (OTF), nonlinear response to light for the full range of luminance, and local adaptation. To calibrate our HDR VDP we perform experiments using an advanced HDR display, capable of displaying the range of luminance that is close to that found in real scenes.
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. Copyright HDR-VDP-2.2: a calibrated method for objective quality prediction of high-dynamic range and standard images: a calibrated method for objective quality prediction of high-dynamic range and standard images
To provide a convincing proof that a new method is better than the state of the art, computer graphics projects are often accompanied by user studies, in which a group of observers rank or rate results of several algorithms. Such user studies, known as subjective image quality assessment experiments, can be very time‐consuming and do not guarantee to produce conclusive results. This paper is intended to help design efficient and rigorous quality assessment experiments and emphasise the key aspects of the results analysis. To promote good standards of data analysis, we review the major methods for data analysis, such as establishing confidence intervals, statistical testing and retrospective power analysis. Two methods of visualising ranking results together with the meaningful information about the statistical and practical significance are explored. Finally, we compare four most prominent subjective quality assessment methods: single‐stimulus, double‐stimulus, forced‐choice pairwise comparison and similarity judgements. We conclude that the forced‐choice pairwise comparison method results in the smallest measurement variance and thus produces the most accurate results. This method is also the most time‐efficient, assuming a moderate number of compared conditions.
Image processing often involves an image transformation into a domain that is better correlated with visual perception, such as the wavelet domain, image pyramids, multi-scale contrast representations, contrast in retinex algorithms, and chroma, lightness and colorfulness predictors in color appearance models. Many of these transformations are not ideally suited for image processing that significantly modifies an image. For example, the modification of a single band in a multi-scale model leads to an unrealistic image with severe halo artifacts. Inspired by gradient domain methods we derive a framework that imposes constraints on the entire set of contrasts in an image for a full range of spatial frequencies. This way, even severe image modifications do not reverse the polarity of contrast. The strengths of the framework are demonstrated by aggressive contrast enhancement and a visually appealing tone mapping which does not introduce artifacts. Additionally, we perceptually linearize contrast magnitudes using a custom transducer function. The transducer function has been derived especially for the purpose of HDR images, based on the contrast discrimination measurements for high contrast stimuli.
Image processing often involves an image transformation into a domain that is better correlated with visual perception, such as the wavelet domain, image pyramids, multi-scale contrast representations, contrast in retinex algorithms, and chroma, lightness and colorfulness predictors in color appearance models. Many of these transformations are not ideally suited for image processing that significantly modifies an image. For example, the modification of a single band in a multi-scale model leads to an unrealistic image with severe halo artifacts. Inspired by gradient domain methods we derive a framework that imposes constraints on the entire set of contrasts in an image for a full range of spatial frequencies. This way, even severe image modifications do not reverse the polarity of contrast. The strengths of the framework are demonstrated by aggressive contrast enhancement and a visually appealing tone mapping which does not introduce artifacts. Additionally, we perceptually linearize contrast magnitudes using a custom transducer function. The transducer function has been derived especially for the purpose of HDR images, based on the contrast discrimination measurements for high contrast stimuli.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.