Showing papers on "Tone mapping published in 2021"

TMO-Net: A Parameter-Free Tone Mapping Operator Using Generative Adversarial Network, and Performance Benchmarking on Large Scale HDR Dataset

Abstract: Currently published tone mapping operators (TMO) are often evaluated on a very limited test set of high dynamic range (HDR) images. Thus, the resulting performance index is highly subject to extensive hyperparameter tuning, and many TMOs exhibit sub-optimal performance when tested on a broader spectrum of HDR images. This indicates that there are deficiencies in the generalizable applicability of these techniques. Finally, it is a challenge developing parameter-free tone mapping operators using data-hungry advanced deep learning methods due to the paucity of large scale HDR datasets. In this paper, these issues are addressed through the following contributions: a) a large scale HDR image benchmark dataset (LVZ-HDR dataset) with multiple variations in sceneries and lighting conditions is created to enable performance evaluation of TMOs across a diverse conditions and scenes that will also contribute to facilitate the development of more robust TMOs using state-of-the-art deep learning methods; b) a deep learning-based tone mapping operator (TMO-Net) is presented, which offers an efficient and parameter-free method capable of generalizing effectively across a wider spectrum of HDR content; c) finally, a comparative analysis, and performance benchmarking of 19 state-of-the-art TMOs on the new LVZ-HDR dataset are presented. Standard metrics including the Tone Mapping Quality Index (TMQI), Feature Similarity Index for Tone Mapped images (FSITM), and Natural Image Quality Evaluator (NIQE) are used to qualitatively evaluate the performance index of the benchmarked TMOs. Experimental results demonstrate that the proposed TMO-Net qualitatively and quantitatively outperforms current state-of-the-art TMOs.

Learning Frequency Domain Priors for Image Demoireing.

Abstract: Image demoireing is a multi-faceted image restoration task involving both moire pattern removal and color restoration. In this paper, we raise a general degradation model to describe an image contaminated by moire patterns, and propose a novel multi-scale bandpass convolutional neural network (MBCNN) for single image demoireing. For moire pattern removal, we propose a multi-block-size learnable bandpass filters (M-LBFs), based on a block-wise frequency domain transform, to learn the frequency domain priors of moire patterns. We also introduce a new loss function named Dilated Advanced Sobel loss (D-ASL) to better sense the frequency information. For color restoration, we propose a two-step tone mapping strategy, which first applies a global tone mapping to correct for a global color shift, and then performs local fine tuning of the color per pixel. To determine the most appropriate frequency domain transform, we investigate several transforms including DCT, DFT, DWT, learnable non-linear transform and learnable orthogonal transform. We finally adopt the DCT. Our basic model won the AIM2019 demoireing challenge. Experimental results on three public datasets show that our method outperforms state-of-the-art methods by a large margin.

Exploiting Local Degradation Characteristics and Global Statistical Properties for Blind Quality Assessment of Tone-Mapped HDR Images

Abstract: Tone mapping operators (TMOs) are developed to convert a high dynamic range (HDR) image into a low dynamic range (LDR) one for display with the goal of preserving as much visual information as possible. However, image quality degradation is inevitable due to the dynamic range compression during the tone-mapping process. This accordingly raises an urgent demand for effective quality evaluation methods to select a high-quality tone-mapped image (TMI) from a set of candidates generated by distinct TMOs or the same TMO with different parameter settings. A key element to the success of TMI quality evaluation is to extract effective features that are highly consistent with human perception. Towards this end, this paper proposes a novel blind TMI quality metric by exploiting both local degradation characteristics and global statistical properties for feature extraction. Several image attributes including texture, structure, colorfulness and naturalness are considered either locally or globally. The extracted local and global features are aggregated into an overall quality via regression. Experimental results on two benchmark databases demonstrate the superiority of the proposed metric over both the state-of-the-art blind quality models designed for synthetically distorted images (SDIs) and the blind quality models specifically developed for TMIs.

A Two-stage Deep Network for High Dynamic Range Image Reconstruction

Abstract: Mapping a single exposure low dynamic range (LDR) image into a high dynamic range (HDR) is considered among the most strenuous image to image translation tasks due to exposure-related missing information. This study tackles the challenges of single-shot LDR to HDR mapping by proposing a novel two-stage deep network. Notably, our proposed method aims to reconstruct an HDR image with-out knowing hardware information, including camera response function (CRF) and exposure settings. Therefore, we aim to perform image enhancement task like denoising, exposure correction, etc., in the first stage. Additionally, the second stage of our deep network learns tone mapping and bit-expansion from a convex set of data samples. The qualitative and quantitative comparisons demonstrate that the proposed method can outperform the existing LDR to HDR works with a marginal difference. Apart from that, we collected an LDR image dataset incorporating different camera systems. The evaluation with our collected real-world LDR images illustrates that the proposed method can reconstruct plausible HDR images without presenting any visual artefacts. Code available : https://github.com/sharif-apu/twostageHDR_NTIRE21.

Real-time tone mapping: a survey and cross-implementation hardware benchmark

Abstract: The rising demand for high quality display has ensued active research in high dynamic range (HDR) imaging, which has the potential to replace the standard dynamic range imaging. This is due to HDR’s features like accurate reproducibility of a scene with its entire spectrum of visible lighting and color depth. But this capability comes with expensive capture, display, storage and distribution resource requirements. Also, display of HDR images/video content on an ordinary display device with limited dynamic range requires some form of adaptation. Many adaptation algorithms, widely known as tone mapping (TM) operators, have been studied and proposed in the last few decades. In this paper, we present a comprehensive survey of 60 TM algorithms that have been implemented on hardware for acceleration and real-time performance. In this state-of-the-art survey, we will discuss those TM algorithms which have been implemented on GPU [1]–[12], FPGA [13]–[47], and ASIC [48]–[60] in terms of their hardware specifications and performance. Output image quality is an important metric for TM algorithms. From our literature survey we found that, various objective quality metrics have been used to demonstrate the quality of those algorithms hardware implementation. We have compiled those metrics used in this survey [61], [62], and analyzed the relationship between hardware cost, image quality and computational efficiency. Currently, machine learning-based (ML) algorithms have become an important tool to solve many image processing tasks, and this paper concludes with a discussion on the future research directions to realize ML-based TM operators on hardware.

Quality Measurement for High Dynamic Range Omnidirectional Image Systems

Abstract: From the perspective of optimizing the visual experience of the omnidirectional system, this article explores the terminal image quality of the high dynamic range omnidirectional image (HOI) system for the first time. The HOI system has higher contrast and wider field of view perception, but its complex imaging process poses a challenge to quality measurement. In this article, we propose a novel quality measurement method for HOI (QM-HOI) system based on distortion perception and brain information-processing mechanism. Because HOI system may encounter single distortion or mixed distortion, the proposed method consists of two modules, i.e., local progressive distortion model (LPDM) and global mixed distortion model (GMDM). LPDM is designed to mainly extract local features based on the different perception effects that tone mapping (TM) operators impart to coding distortion in different luminance regions. GMDM is designed to jointly consider the structure distortion caused by coding and the color distortion of TM. The extracted features are formed into feature vectors to predict the visual quality of the distorted HOIs. A new HOI subjective evaluation dataset with multidistortion is established, called NBU-HOID, specialized for the design and testing of the proposed method. Experimental results show that the objective measurement results of the proposed method is better than the state-of-the-art methods, and more in line with the human perception. We will also provide the NBU-HOID dataset free of charge shortly afterward.

Structure revealing of low-light images using wavelet transform based on fractional-order denoising and multiscale decomposition

Abstract: Images captured in low-light environment often lower its quality due to low illumination and high noise. Hence, the low visibility of images notably degrades the overall performance of multimedia and vision systems that are typically designed for high-quality inputs. To resolve this problem, numerous algorithms have been proposed in extant literature to improve the visual quality of low-light images. However, existing approaches are not good at improving overexposed portions and produce unnecessary distortion, which leads to poor visibility in images. Therefore, in this paper, a new model is proposed to prevent overenhancement, handle uneven illumination, and suppress noise in underexposed images. Firstly, the input image is converted into HSV color space. Then, the obtained V component is decomposed into high- and low-frequency subbands using the dual-tree complex wavelet transform. Secondly, a denoised model based on fractional-order anisotropic diffusion is applied on high-pass subbands. Thirdly, multiscale decomposition is used to extract more details from low-pass subbands, and inverse transformation is performed to compute final V. Next, sigmoid function and tone mapping are used on V-channel to prevent data loss and achieve robust results. Finally, the image is reconstructed and converted to RGB color space to achieve enhanced performance. Comparative experimental statistics show that the proposed method achieves high efficacy and outperforms the traditional approaches in terms of overall performance.

Deep Tone-Mapping Operator Using Image Quality Assessment Inspired Semi-Supervised Learning

Abstract: Tone-mapping operator (TMO) is intended to convert high dynamic range (HDR) content into a lower dynamic range so that it can be displayed on a standard dynamic range (SDR) device. The tone-mapped result of HDR content is usually stored as SDR image. For different HDR scenes, traditional TMOs are able to obtain a satisfying SDR image only under manually fine-tuned parameters. In this paper, we address this problem by proposing a learning-based TMO using deep convolutional neural network (CNN). We explore different CNN structure and adopt multi-scale and multi-branch fully convolutional design. When training deep CNN, we introduce image quality assessments (IQA), specifically, tone-mapped image quality assessment, and implement it as semi-supervised loss terms. We discuss and prove the effectiveness of semi-supervised loss terms, CNN structure, data pre-processing, etc. by several experiments. Finally, we demonstrate that our approach can produce appealing results under diversified HDR scenes.

Spatially Aware Metadata for Raw Reconstruction

Abstract: A camera sensor captures a raw-RGB image that is then processed to a standard RGB (sRGB) image through a series of onboard operations performed by the camera’s image signal processor (ISP). Among these processing steps, local tone mapping is one of the most important operations used to enhance the overall appearance of the final rendered sRGB image. For certain applications, it is often desirable to de-render or unprocess the sRGB image back to its original raw-RGB values. This "raw reconstruction" is a challenging task because many of the operations performed by the ISP, including local tone mapping, are nonlinear and difficult to invert. Existing raw reconstruction methods that store specialized metadata at capture time to enable raw recovery ignore local tone mapping and assume that a global transformation exists between the raw-RGB and sRGB color spaces. In this work, we advocate a spatially aware metadata-based raw reconstruction method that is robust to local tone mapping, and yields significantly higher raw reconstruction accuracy (6 dB average PSNR improvement) compared to existing raw reconstruction methods. Our method requires only 0.2% samples of the full-sized image as metadata, has negligible computational overhead at capture time, and can be easily integrated into modern ISPs.

A Real-Time Semi-Supervised Deep Tone Mapping Network

Abstract: Tone mapping operators (TMOs) can compress the range of high dynamic range (HDR) images so that they can be displayed normally on the low dynamic range (LDR) devices. Recent TMOs based on deep neural networks can produce impressive results, but there are still some shortcomings. On the one hand, their supervised learning procedure requires a high-quality paired dataset which is hard to be accessed. On the other hand, they are too slow and heavy to meet the needs of practical applications. This paper proposes a real-time deep semi-supervised learning TMO to solve the above problems. The proposed method learns in a semi-supervised manner by combining the adversarial loss, cycle consistency loss, and the pixel-wise loss. The first two can simulate the image distributions in the real world from the unpaired LDR data and the latter can learn the guidance of paired LDR labels. In this way, the proposed method only requires HDR sources, unpaired high-quality LDR images, and a few well tone-mapped HDR-LDR pairs as training data. Furthermore, the proposed method divides tone mapping into luminance mapping and saturation adjustment and then processes them simultaneously. By this strategy, we can reconstruct each component more precisely. Based on the aforementioned improvements, we propose a lightweight tone mapping network that is efficient in tone mapping task (up to 5000x parameters-saving and 27x time-saving compared to the learning-based TMOs). Both quantitative and qualitative results demonstrate that the proposed method performs favorable against state-of-the-art TMOs.

Obstacle Distance Measurement Under Varying Illumination Conditions Based on Monocular Vision Using a Cable Inspection Robot

Abstract: Obstacle distance measurement is one of the key technologies for autonomous navigation of high-voltage transmission line inspection robots. To address the robustness of obstacle distance measurement under varying illumination conditions, this article develops a research method that fuses image enhancement with robot monocular vision so that the robot can adapt to various levels of illumination running along the transmission line. During the inspection of high-voltage transmission lines in such an overexposed (excessively bright) environment, a specular highlight suppression method is proposed to suppress the specular reflections in an image; when scene illumination is insufficient, a robust low-light image enhancement method based on a tone mapping algorithm with weighted guided filtering is presented. Based on the monocular vision measurement principle, the error generation mechanism is analyzed through experiments, and we introduce the parameter modification mechanism. The two proposed image enhancement methods outperform other state-of-the-art enhancement algorithms in qualitative and quantitative analyses. The experimental results show that the measurement error is less than 3% for static distance measurements and less than 5% for dynamic distance measurements within 6 m. The proposed method can meet the requirements of high-accuracy positioning, real-time performance and strong robustness. This method greatly contributes to the sustainable development of inspection robots in the power industry.

Visible and Near-Infrared Image Acquisition and Fusion for Night Surveillance

Abstract: Image fusion combines images with different information to create a single, information-rich image. The process may either involve synthesizing images using multiple exposures of the same scene, such as exposure fusion, or synthesizing images of different wavelength bands, such as visible and near-infrared (NIR) image fusion. NIR images are frequently used in surveillance systems because they are beyond the narrow perceptual range of human vision. In this paper, we propose an infrared image fusion method that combines high and low intensities for use in surveillance systems under low-light conditions. The proposed method utilizes a depth-weighted radiance map based on intensities and details to enhance local contrast and reduce noise and color distortion. The proposed method involves luminance blending, local tone mapping, and color scaling and correction. Each of these stages is processed in the LAB color space to preserve the color attributes of a visible image. The results confirm that the proposed method outperforms conventional methods.

Real-Time Deep Image Retouching Based on Learnt Semantics Dependent Global Transforms

Abstract: Although artists’ actions in photo retouching appear to be highly nonlinear in nature and very difficult to characterize analytically, we find that the net effects of interactively editing a mundane image to a desired appearance can be modeled, in most cases, by a parametric monotonically non-decreasing global tone mapping function in the luminance axis and by a global affine transform in the chrominance plane that are weighted by saliency. This allows us to simplify the machine learning problem of mimicking artists in photo retouching to constructing a deep artful image transform (DAIT) using convolutional neural networks (CNN). The CNN design of DAIT aims to learn the image-dependent parameters of the luminance tone mapping function and the affine chrominance transform, rather than learning the end-to-end pixel level mapping as in the mainstream methods of image restoration and enhancement. The proposed DAIT approach reduces the computation complexity of the neural network by two orders of magnitude, which also, as a side benefit, improves the robustness and generalization capability at the inference stage. The high throughput and robustness of DAIT lend itself readily to real-time video enhancement as well after a simple temporal processing. Experiments and a Turing-type test are conducted to evaluate the proposed method and its competitors.

Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies

Abstract: Many challenges that deal with processing of HDR material remain very much open for the film industry, whose extremely demanding quality standards are not met by existing automatic methods. Therefore, when dealing with HDR content, substantial work by very skilled technicians has to be carried out at every step of the movie production chain. Based on recent findings and models from vision science, we propose in this work effective tone mapping and inverse tone mapping algorithms for production, post-production and exhibition. These methods are automatic and real-time, and they have been both fine-tuned and validated by cinema professionals, with psychophysical tests demonstrating that the proposed algorithms outperform both the academic and industrial state-of-the-art. We believe these methods bring the field closer to having fully automated solutions for important challenges for the cinema industry that are currently solved manually or sub-optimally. Another contribution of our research is to highlight the limitations of existing image quality metrics when applied to the tone mapping problem, as none of them, including two state-of-the-art deep learning metrics for image perception, are able to predict the preferences of the observers.

Enhancing the Surveillance Detection Range of Image Sensors Using HDR Techniques

Abstract: Image sensor-based surveillance systems are used for scene analysis, image sequence creation, and object detection. Natural scenes contain areas of high and low illumination, and standard cameras can only transform a fraction of the available visual information. The wide variation in illumination conditions limits the detection capabilities of image sensors. Therefore, in this study, the feasibility of applying high dynamic range (HDR) techniques using image sensors for enhancing range performance was investigated. The HDR requirements were analyzed, and available HDR techniques along with tone mapping and image enhancement were optimized for real-time scenarios. To determine the HDR requirements for specific visibility conditions, a theoretical analysis was conducted to evaluate camera performance using the human visual system. Additionally, a HDR imaging framework was established, and experiments were conducted to validate the performance of the framework. Results demonstrate that there is an empirical relationship between the dynamic range and visual detection range of the surveillance system. Subjective and objective evaluations indicate that surveillance cameras employing HDR imaging for long range applications have increased target detection range.

A Novel HDR Image Zero-Watermarking Based on Shift-Invariant Shearlet Transform

Abstract: In this paper, a novel high dynamic range (HDR) image zero-watermarking algorithm against the tone mapping attack is proposed. In order to extract stable and invariant features for robust zero-watermarking, the shift-invariant shearlet transform (SIST) is used to transform the HDR image. Firstly, the HDR image is converted to CIELAB color space, and the L component is selected to perform SIST for obtaining the low-frequency subband containing the robust structure information of the image. Secondly, the low-frequency subband is divided into nonoverlapping blocks, which are transformed by using discrete cosine transform (DCT) and singular value decomposition (SVD) to obtain the maximum singular values for constructing a binary feature image. To increase the watermarking security, a hybrid chaotic mapping (HCM) is employed to get the scrambled watermark. Finally, an exclusive-or operation is performed between the binary feature image and the scrambled watermark to compute robust zero-watermark. Experimental results show that the proposed algorithm has a good capability of resisting tone mapping and other image processing attacks.

Deep Reformulated Laplacian Tone Mapping.

Abstract: Wide dynamic range (WDR) images contain more scene details and contrast when compared to common images. However, it requires tone mapping to process the pixel values in order to display properly. The details of WDR images can diminish during the tone mapping process. In this work, we address the problem by combining a novel reformulated Laplacian pyramid and deep learning. The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented. The reformulation preserves the local features in its original resolution and condenses the global features into a low-resolution image. The generated frequency bands are reconstructed and fine-tuned to output the final tone mapped image that can display on the screen with minimum detail and contrast loss. The experimental results demonstrate that the proposed method outperforms state-of-the-art WDR image tone mapping methods. The code is made publicly available at this https URL.

HDR-NeRF: High Dynamic Range Neural Radiance Fields.

Abstract: 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. Using the HDR-NeRF, we are able to generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper. The radiance field encodes the scene radiance (values vary from 0 to +infty), which outputs the density and radiance of a ray by giving corresponding ray origin and ray direction. The tone mapper models the mapping process that a ray hitting on the camera sensor becomes a pixel value. The color of the ray is predicted by feeding the radiance and the corresponding exposure time into the tone mapper. We use the classic volume rendering technique to project the output radiance, colors, and densities into HDR and LDR images, while only the input LDR images are used as the supervision. We collect a new forward-facing HDR dataset to evaluate the proposed method. Experimental results on synthetic and real-world scenes validate that our method can not only accurately control the exposures of synthesized views but also render views with a high dynamic range.

A non-uniform quantization scheme for visualization of CT images.

Abstract: Medical science heavily depends on image acquisition and post-processing for accurate diagnosis and treatment planning. The introduction of noise degrades the visual quality of the medical images during the capturing process, which may result in false perception. Therefore, medical image enhancement is an essential topic of research for the improvement of image quality. In this paper, a clustering-based contrast enhancement technique is presented for computed tomography (CT) images. Our approach uses the recursive splitting of data into clusters targeting the maximum error reduction in each cluster. This leads to grouping similar pixels in every cluster, maximizing inter-cluster and minimizing intra-cluster similarities. A suitable number of clusters can be chosen to represent high precision data with the desired bit-depth. We use 256 clusters to convert 16-bit CT scans to 8-bit images suitable for visualization on standard low dynamic range displays. We compare our method with several existing contrast enhancement algorithms and show that the proposed technique provides better results in terms of execution efficiency and quality of enhanced images.

Explorable Tone Mapping Operators

Abstract: Tone-mapping plays an essential role in high dynamic range (HDR) imaging. It aims to preserve visual information of HDR images in a medium with a limited dynamic range. Although many works have been proposed to provide tone-mapped results from HDR images, most of them can only perform tone-mapping in a single pre-designed way. However, the subjectivity of tone-mapping quality varies from person to person, and the preference of tone-mapping style also differs from application to application. In this paper, a learning-based multimodal tone-mapping method is proposed, which not only achieves excellent visual quality but also explores the style diversity. Based on the framework of BicycleGAN [1], the proposed method can provide a variety of expert-level tone-mapped results by manipulating different latent codes. Finally, we show that the proposed method performs favorably against state-of-the-art tone-mapping algorithms both quantitatively and qualitatively.

Two-layer pyramid-based blending method for exposure fusion

Abstract: Multi-exposure fusion is a technique used to generate a high-dynamic-range image without calculating the camera response function and without compressing its ranges with the tone mapping process. There are many schemes for fusing multi-exposure images. One of the famous schemes is the pyramid-based blending, which fuses multi-exposure images together based on the concept of multi-resolution blending. The computational time of this method is fast, and the resulting image is satisfying. However, in some cases, the pyramid-based blending method has a trade-off between preserving local areas and the quality in terms of smoothness boundaries. To solve this trade-off, we propose a new pyramid-based blending scheme, called the two-layer pyramid-based blending method for multi-exposure fusion. We found that, for some sets of input images, we have to generate a virtual photograph and add it into those sets. Thus, we first propose a criterion for adding the virtual photograph. Then, we construct a concatenation of two pyramid-based blending methods, in which the resulting images from different levels of the first-layer pyramid-based blending method are used as inputs of the second-layer one. The test results showed that the resulting images were satisfying, and their objective evaluation scores regarding the perceptual image quality and detail-preserving assessment were high, even though they are not highest, compared with those of methods used in our experiments. Also, there is one advantage of the proposed method compared with the others. That is, the proposed method could preserve details in some areas, whereas the other methods could not.

Pencil Drawing Generation Algorithm Based on GMED

Abstract: The automatic generation of pencil drawings from natural images has been a hot spot in the field of nonphotorealistic rendering in recent years and has attracted the attention of many scholars. Aiming at the characteristics of single line drawings generated by the existing pencil drawing algorithm and stiff lines, this paper proposes a new edge generation Gradlent Morphological Edge Detector (GMED) algorithm, which uses the generated edge convolution to generate pencil line drawings, making stylized pictures more natural. First, the gradient map of the input image is extracted according to the feature of the tone rate of change around the line at the boundary. Second, to make up for the shortcomings of too thin and discontinuous lines in the gradient map, morphological operations are performed on the gradient map and convolved to generate a hand-drawn pencil line drawing. Finally, texture filling and tone mapping are performed, and the resulting line drawing is fused to obtain the final pencil drawing effect. Compared with the existing pencil drawing algorithm, the proposed GMED edge generation method is applied to the line drawing generation process to generate a hand-drawn style, fine and concise line drawing, and the texture simulation process is simple and efficient, combined with histogram matching. In the process, a more suitable GML method is used, so that the final pencil drawing not only has natural lines but also colors closer to the input image.

Robust HDR video watermarking method based on saliency extraction and T-SVD

Abstract: In order to protect the copyright of the high dynamic range (HDR) video, a robust HDR video watermarking method based on saliency extraction and tensor-singular value decomposition (T-SVD) is proposed. Since T-SVD can not only represent high-dimension data, but also remain its intrinsic structure, each frame of the HDR video is considered as the third-order tensor to be transformed by using T-SVD for preserving the main characteristics of the frame. Each frame is divided into non-overlapping blocks, and each block is decomposed by using T-SVD to obtain the orthogonal tensor $${\mathcal{U}}$$ , which includes three orthogonal matrices and represents main energies of the frame. Since the second matrix has more correlations of the video frame than other two matrices, it is used to embed watermark for robustness. Moreover, to obtain the trade-off between watermarking robustness and the visual quality, the saliency map of each frame is extracted to predict the most relevant and important areas for determining the watermark embedding strength. The saliency map is computed based on fusing the spatial saliency and the temporal saliency, where the spatial saliency is built by calculating color, intensity and orientation features of the HDR video and the temporal saliency is obtained by using the optical flow. Experiment results show that the proposed watermarking method can resist a variety of tone mapping attacks and video attacks, and is more robust than existing watermarking methods.

A Novel Zero Watermarking Based on DT-CWT and Quaternion for HDR Image

Abstract: This paper presents a high dynamic range (HDR) image zero watermarking method based on dual tree complex wavelet transform (DT-CWT) and quaternion. In order to be against tone mapping (TM), DT-CWT is used to transform the three RGB color channels of the HDR image for obtaining the low-pass sub-bands, respectively, since DT-CWT can extract the contour of the HDR image and the contour change of the HDR image is small after TM. The HDR image provides a wide dynamic range, and thus, three-color channel correlations are higher than inner-relationships and the quaternion is used to consider three color channels as a whole to be transformed. Quaternion fast Fourier transform (QFFT) and quaternion singular value decomposition (QSVD) are utilized to decompose the HDR image for obtaining robust features, which is fused with a binary watermark to generate a zero watermark for copyright protection. Furthermore, the binary watermark is scrambled for the security by using the Arnold transform. Experimental results denote that the proposed zero-watermarking method is robust to TM and other image processing attacks, and can protect the HDR image efficiently.

A Re-examination of Dichoptic Tone Mapping

Abstract: Dichoptic tone mapping methods aim to leverage stereoscopic displays to increase visual detail and contrast in images and videos. These methods, which have been called both binocular tone mapping and dichoptic contrast enhancement, selectively emphasize contrast differently in the two eyes’ views. The visual system integrates these contrast differences into a unified percept, which is theorized to contain more contrast overall than each eye’s view on its own. As stereoscopic displays become increasingly common for augmented and virtual reality (AR/VR), dichoptic tone mapping is an appealing technique for imaging pipelines. We sought to examine whether a standard photographic technique, exposure bracketing, could be modified to enhance contrast similarly to dichoptic tone mapping. While assessing the efficacy of this technique with user studies, we also re-evaluated existing dichoptic tone mapping methods. Across several user studies; however, we did not find evidence that either dichoptic tone mapping or dichoptic exposures consistently increased subjective image preferences. We also did not observe improvements in subjective or objective measures of detail visibility. We did find evidence that dichoptic methods enhanced subjective 3D impressions. Here, we present these results and evaluate the potential contributions and current limitations of dichoptic methods for applications in stereoscopic displays.

Image data pre-processing for neural networks

Abstract: Image data 310 (e.g. pixel data) obtained from an image sensor undergoes an image processing operation 330i (e.g. white balance, shading correction, tone mapping). Characteristic data (e.g. shot noise, dark current noise, read noise) of the image data is separately processed by applying an operation 330n associated with the image processing operation 330i (so that the result is representative of the characteristic data as it is processed with the image data). The output processed image data and characteristic data 340 is suitable for use by a neural network 350, so that there is no need for the neural network to perform de-noising to distinguish characteristic data from data to be used in training or classification tasks. Image and characteristic data processing may be performed in parallel and, for high dynamic range image data, an exposure mask based on a boundary associated with the HDR data may be generated at the same time.

Savitzky–Golay Filtering-Based Fusion of Multiple Exposure Images for High Dynamic Range Imaging

Abstract: The problem of compositing multiple exposure images has attracted lots of researchers, over the past years. It all began with the problem of High Dynamic Range (HDR) imaging, for capturing scenes with vast differences in their dynamic range. Fine details in all the areas in these scenes cannot be captured with one single exposure setting of the camera aperture. This leads to multiple exposure images with each image containing accurate representation of different regions dimly lit, well lit and brightly lit in the scenes. One can make a combined HDR image out of these multiple exposure shots. This combination of multiple exposure shots leads to an image of a higher dynamic range in a different image format which cannot be represented in the traditional Low Dynamic Range (LDR) formats. Moreover HDR images cannot be displayed in traditional display devices suitable for LDR. So these images have to undergo a process called as tone mapping for further converting them to be suitable enough to be represented on usual LDR displays. An approach based on Savitzky–Golay parametric filtering which preserves edges, is proposed which uses filtered multiple exposure images to generate the alpha matte coefficients required for fusing the input multiple exposure set. The coefficients generated in the proposed approach helps in retaining the weak edges and the fine textures which are lost as a result of the under and over exposures. The proposed approach is similar in nature to the bilateral filter-based compositing approach for multiple exposure images in the literature but it is novel, in exploring the possibility of compositing using a parametric filtering approach. The proposed approach performs the fusion in the LDR domain and the fused output can also be displayed using standard LDR image formats on standard LDR displays. A brief comparison of the results generated by the proposed method and various other approaches, including the traditional exposure fusion, tone mapping-based techniques and bilateral filter-based approach is presented where in the proposed method compares well and fares better in majority of the test cases.

HD-RACE: Spray-based Local Tone Mapping Operator

Abstract: In this paper, a local tone mapping operator is proposed. It is based on the theory of sprays introduced in the Random Sprays Retinex algorithm, a white balance algorithm dealing with the locality of color perception. This tone mapping implementation compresses high dynamic range images by using three types of computations on sprays. These operations are carefully chosen so that the result of their convex combination is a low dynamic range image with a high level of detail in all its parts regardless of the original luminance values that may span over large dynamic ranges. Furthermore, a simple local formulation of the Naka-Rushton equation based on random sprays is given. The experimental results are presented and discussed.

An enhancement framework based on gradient domain tone mapping and fuzzy logical for X-ray image of complex workpiece

Abstract: X-ray images of complex workpiece often suffer low brightness and contrast in industrial defect inspection. In this paper, we propose an enhancement framework to improve the visual quality. In detail, a logarithm transformation is first to increase global brightness, and then, to increase local contrast, we propose a novel gradient domain tone mapping operator, in which we design a new gradient attenuation function based on fuzzy entropy and construct a new cost function constrained by a hybrid regularization. Finally a fuzzy enhancement operator is performed on the result obtained by minimizing the new cost function, to further increase contrast and prevent halo artifacts created by manipulating the gradient domain. Experiments show that the proposed method produces good visual effect for defect inspection for X-ray image of complex workpiece.