Tone Mapping Research Articles

Multiexposed Image-Fusion Strategy Using Mutual Image Translation Learning with Multiscale Surround Switching Maps

The dynamic range of an image represents the difference between its darkest and brightest areas, a crucial concept in digital image processing and computer vision. Despite display technology advancements, replicating the broad dynamic range of the human visual system remains challenging, necessitating high dynamic range (HDR) synthesis, combining multiple low dynamic range images captured at contrasting exposure levels to generate a single HDR image that integrates the optimal exposure regions. Recent deep learning advancements have introduced innovative approaches to HDR generation, with the cycle-consistent generative adversarial network (CycleGAN) gaining attention due to its robustness against domain shifts and ability to preserve content style while enhancing image quality. However, traditional CycleGAN methods often rely on unpaired datasets, limiting their capacity for detail preservation. This study proposes an improved model by incorporating a switching map (SMap) as an additional channel in the CycleGAN generator using paired datasets. The SMap focuses on essential regions, guiding weighted learning to minimize the loss of detail during synthesis. Using translated images to estimate the middle exposure integrates these images into HDR synthesis, reducing unnatural transitions and halo artifacts that could occur at boundaries between various exposures. The multilayered application of the retinex algorithm captures exposure variations, achieving natural and detailed tone mapping. The proposed mutual image translation module extends CycleGAN, demonstrating superior performance in multiexposure fusion and image translation, significantly enhancing HDR image quality. The image quality evaluation indices used are CPBDM, JNBM, LPC-SI, S3, JPEG_2000, and SSEQ, and the proposed model exhibits superior performance compared to existing methods, recording average scores of 0.6196, 15.4142, 0.9642, 0.2838, 80.239, and 25.054, respectively. Therefore, based on qualitative and quantitative results, this study demonstrates the superiority of the proposed model.

Skin Tone Analysis Through Skin Tone Map Generation With Optical Approach and Deep Learning.

Skin tone assessment is critical in both cosmetic and medical fields, yet traditional methods like the individual typology angle (ITA) have limitations, such as sensitivity to illuminants and insensitivity to skinredness. This study introduces an automated image-based method for skin tone mapping by applying optical approaches and deep learning. The method generates skin tone maps by leveraging the illuminant spectrum, segments the skin region from face images, and identifies the corresponding skin tone on the map. The method was evaluated by generating skin tone maps under three standard illuminants (D45, D65, and D85) and comparing the results with those obtained using ITA on skin tone simulationimages. The results showed that skin tone maps generated under the same lighting conditions as the image acquisition (D65) provided the highest accuracy, with a color difference of around 6, which is more than twice as small as those observed under other illuminants. The mapping positions also demonstrated a clear correlation with pigment levels. Compared to ITA, the proposed approach was particularly effective in distinguishing skin tones related toredness. Despite the need to measure the illuminant spectrum and for further physiological validation, the proposed approach shows potential for enhancing skin tone assessment. Its ability to mitigate the effects of illuminants and distinguish between the two dominant pigments offers promising applications in both cosmetic and medicaldiagnostics.

Analyze the impact of nonlinear distortions on OFDM-based visible light communication systems

Visible light communication (VLC) has gained attraction for its use in high-speed wireless connectivity leveraging LED lighting elements. Orthogonal Frequency Division Multiplexing (OFDM) is an attractive modulation scheme due to its spectral efficiency and resilience to multipath distortion. However, the nonlinear electro-optic transfer characteristics of optical components introduce signal clipping and quantization noise which corrupt OFDM signals. This paper provides an in-depth analysis of clipping and quantization noise to quantify the impact of LED nonlinearities on OFDM-based VLC system performance. Detailed mathematical models are derived for clipping distortions caused by LED optical power saturation and quantization errors from ADC/DAC finite precision in the modulator and driver circuitry. This analysis is quantified through simulations of the degradations in terms of error vector magnitude (EVM), signal-to-noise ratio (SNR) loss, and bit error rate (BER) under varying clipping ratios and quantization bit-depths. The 16-QAM OFDM transmission shows that the LED driver should possess at least 12 dB signal linear dynamic range and 3-bit quantization to restrict SNR penalty within 3 dB. Adaptive tone mapping and digital pre-distortion techniques are examined to compensate for intensity distortions enabling high-speed OFDM transmission over VLC links.

High dynamic range image tone mapping based on variational image decomposition and color correction

Tone mapping aims to reproduce high dynamic range (HDR) images on low dynamic range (LDR) display devices. The layer-decomposition-based tone mapping algorithms usually decompose HDR images into base and detail layers and process them accordingly. Since the detail layer is not refined again, these algorithms may suffer from halo artifacts, relatively dull color, and over-enhancement problems. To solve these problems, we introduce the variational image decomposition model and color correction into the field of tone mapping, and propose a tone mapping algorithm that combines the three-part variational image decomposition model with a color correction scheme based on minimum color loss. In contrast to traditional layer-decomposition-based tone mapping algorithms, we employ the three-part decomposition model that decomposes the HDR image into three components: a cartoon component, a texture component, and a high-frequency detail component. The cartoon component is compressed using a gamma function, while the texture and high-frequency detail components are each enhanced using the nonlinear stretching functions. This approach allows for better detail enhancement while preserving the smoothness of the image. In addition, we further use the color correction scheme based on minimum color loss to solve the color problem caused by the layer-decomposition-based tone mapping algorithms. Experimental results show that our proposed tone mapping algorithm can reduce the halo artifacts and preserve the edge details while outperforming some state-of-the-art tone mapping algorithms.

Tone mapping algorithm based on BL-Hilbert-L 2 decomposition model for HDR image

Abstract Tone mapping algorithms are mainly used to produce standard dynamic range (SDR) images from high dynamic range (HDR) images. To address the issues of halo artifacts and over-enhancement in current tone mapping algorithms based on layer decomposition model, we propose a tone mapping algorithm based on the BL-Hilbert-L2 decomposition model. In our proposed algorithm, we first convert HDR image from RGB space to HSV space. Subsequently, utilizing the BL-Hilbert-L2 decomposition model, we decompose the V channel of the HDR image into cartoon, texture and high-frequency detail components. Next, we separately compress the cartoon component and stretch the texture and high-frequency detail components. The processed cartoon, texture and high-frequency detail components are then recombined to form a new V channel. Finally, by converting the H and S channels of the HDR image, along with the newly formed V channel, back into the RGB color space, we obtain a tone mapped SDR image. Experimental results demonstrate that our proposed algorithm can effectively eliminate the halo artifacts and avoid the issue of over-enhancement while retaining the edge details.

Generic color correction for tone mapping operators in high dynamic range imaging

One of the significant challenges in tone mapping is to preserve the perceptual quality of the tone-mapped images. Traditional tone mapping operators (TMOs) compress the luminance of high dynamic range (HDR) images with little to no consideration of image color information resulting into suboptimal colors. Existing color management algorithms require either manual parameter tuning or introducing lightness and hue shifts. The current study aimed to develop a color correction model in plausible agreement with the psychophysical phenomenon of color appearance perception for optimal color reproduction of tone mapped images. The proposed model leverages CIECAM16 perceptual correlates i.e., lightness, chroma, and hue. It is adaptive and entirely automatic while preserving the lightness of the tone-mapped image and maintaining the hue from the HDR image. Moreover, it does not require any gamut mapping correction algorithm in natural color reproduction. The effectiveness of the model was validated using objective and subjective methods. The experiments revealed that the model achieved optimal color reproduction in terms of the naturalness of the colors.

Multi-stage coarse-to-fine progressive enhancement network for single-image HDR reconstruction

Compared with traditional imaging, high dynamic range (HDR) imaging technology can record scene information more accurately, thereby providing users higher quality of visual experience. Inverse tone mapping is a direct and effective way to realize single-image HDR reconstruction, but it usually suffers from some problems such as detail loss, color deviation and artifacts. To solve the problems, this paper proposes a multi-stage coarse-to-fine progressive enhancement network (named MSPENet) for single-image HDR reconstruction. The entire multi-stage network architecture is designed in a progressive manner to obtain higher-quality HDR images from coarse-to-fine, where a mask mechanism is used to eliminate the effects of over-exposure regions. Specifically, in the first two stages, two asymmetric U-Nets are constructed to learn the multi-scale information of input image and perform coarse reconstruction. In the third stage, a residual network with channel attention mechanism is constructed to learn the fusion of progressively transferred multi-level features and perform fine reconstruction. In addition, a multi-stage progressive detail enhancement mechanism is designed, including progressive gated recurrent unit fusion mechanism and multi-stage feature transfer mechanism. The former fuses the progressively transferred features with coarse HDR features to reduce the error stacking effect caused by multi-stage networks. Meanwhile, the latter fuses early features to supplement the lost information during each stage of feature delivery and combines features from different stages. Extensive experimental results show that the proposed method can reconstruct higher quality HDR images and effectively recover texture and color information in over-exposure regions compared to the state-of-the-art methods.

Enhancing a Display’s Sunlight Readability with Tone Mapping

The sunlight readability of display devices, such as notebook computers, transparent displays, vehicle displays, and augmented reality, is a significant technical challenge due to degraded image quality. To mitigate this problem, by fitting the human eye function, we propose a tone mapping method on a mobile phone display panel to enhance low grayscale image readability under bright ambient light. Additionally, we adapt a mini-LED backlight model to simulate real images under different ambient lighting conditions. Both experimental and simulated results indicate that high luminance displays with an optimized gamma value significantly enhance sunlight readability and image quality. Moreover, global color rendering can alleviate color shift. Such a method is also valid for the optimization of optical see-through devices under diverse environmental conditions.

The feature enhancement method of artistic images based on histogram equalization and bilateral filtering

To improve the rendering effect of artistic images, a method enhancing features of artistic images is proposed based on histogram equalization and bilateral filtering in the article. Firstly, artistic images are divided into both high and low-frequency representations, and the multi-step enhancement processing level is delimited by multi-band decomposition. Secondly, the noise in the image is removed by bilateral filtering. Then, the grey-level histogram of the image is modified by using the histogram equalization. Finally, the features of the artistic image are enhanced by global tone mapping after histogram equalization processing is conducted. Then, the image is sharpened to improve the enhancement effect further. The experiments show that the features of the color and edge details turn out to be more vivid and clearer after the proposed method is implemented. The structural similarity (SSIM) measure of the image increases to 0.973, and the average gradient gets close to 0.8, which shows that the proposed method is effective.

57‐4: Advanced Tone Mapping of Mini‐LED Backlit LCDs for Automotive Displays

Tone mapping and mini‐LED backlight algorithms are applied to enhance the sunlight readability of LCDs by fitting the human eye's functionality and increasing image uniformity. Both experimental and simulation results indicate that high luminance displays with an optimized gamma value help to distinguish low grayscale contents under bright ambient conditions.

Removing Banding Artifacts in HDR Videos Generated From Inverse Tone Mapping

Removing Banding Artifacts in HDR Videos Generated From Inverse Tone Mapping

Efficient Image Details Preservation of Image Processing Pipeline Based on Two-Stage Tone Mapping

Converting a camera’s RAW image to an RGB format for human perception involves utilizing an imaging pipeline, and a series of processing modules. Existing modules often result in varying degrees of original information loss, which can render the reverse imaging pipeline unable to recover the original RAW image information. To this end, this paper proposes a new, almost reversible image imaging pipeline. Thus, RGB images and RAW images can be effectively converted between each other. Considering the impact of original information loss, this paper introduces a two-stage tone mapping operation (TMO). In the first stage, the RAW image with a linear response is transformed into an RGB color image. In the second stage, color scale mapping corrects the dynamic range of the image suitable for human perception through linear stretching, and reduces the loss of sensitive information to the human eye during the integer process. effectively preserving the original image’s dynamic information. The DCRAW imaging pipeline addresses the problem of high light overflow by directly highlighting cuts. The proposed imaging pipeline constructs an independent highlight processing module, and preserves the highlighted information of the image. The experimental results demonstrate that the two-stage tone mapping operation embedded in the imaging processing pipeline provided in this article ensures that the image output is suitable for human visual system (HVS) perception and retains more original image information.

Contrastive learning for deep tone mapping operator

Most existing tone mapping operators (TMOs) are developed based on prior assumptions of human visual system, and they are known to be sensitive to hyperparameters. In this paper, we proposed a straightforward yet efficient framework to automatically learn the priors and perform tone mapping in an end-to-end manner. The proposed algorithm utilizes a contrastive learning framework to enforce the content consistency between high dynamic range (HDR) inputs and low dynamic range (LDR) outputs. Since contrastive learning aims at maximizing the mutual information across different domains, no paired images or labels are required in our algorithm. Equipped with an attention-based U-Net to alleviate the aliasing and halo artifacts, our algorithm can produce sharp and visually appealing images over various complex real-world scenes, indicating that the proposed algorithm can be used as a strong baseline for future HDR image tone mapping task. Extensive experiments as well as subjective evaluations demonstrated that the proposed algorithm outperforms the existing state-of-the-art algorithms qualitatively and quantitatively. The code is available at https://github.com/xslidi/CATMO.

Self-supervised High Dynamic Range Imaging: What Can Be Learned from a Single 8-bit Video?

Recently, Deep Learning-based methods for inverse tone mapping standard dynamic range (SDR) images to obtain high dynamic range (HDR) images have become very popular. These methods manage to fill over-exposed areas convincingly both in terms of details and dynamic range. To be effective, deep learning-based methods need to learn from large datasets and transfer this knowledge to the network weights. In this work, we tackle this problem from a completely different perspective. What can we learn from a single SDR 8-bit video? With the presented self-supervised approach, we show that, in many cases, a single SDR video is sufficient to generate an HDR video of the same quality or better than other state-of-the-art methods.

Analysis and simulation of the effect of large optical range difference of common path coherent-dispersion spectrometer on the detection of exoplanet radial velocities

The Exoplanet Explorer common-path coherent-dispersion spectrometer (CODES) utilizes a unique combination of an asymmetric common path Sagnac interferometer and a low to medium resolution spectrometer. The ideal optical range difference (OPD) interval for CODES is OPD ∈ {15.06 mm, 19.45 mm}; however, the OPD of CODES is 64.3 mm to achieve better detection accuracy. Though they will increase the accuracy of detection, large OPDs outside of the ideal interval will also reduce the contrast of the interference fringes, making phase changes more hazy. This may also significantly affect the radial velocity inversion and reduce CODES's instrumental accuracy. This study creates an inverse tone mapping operator based on the photographic model and designs an inverse tone mapping algorithm called CODESCE. The outcomes of the experiments demonstrate that the tone mapping algorithm CODESCE in this work is appropriate for enhancing the contrast of interference fringe images with high OPD, and it can enhance the contrast of interference fringes by three orders of magnitude when OPD = 64.3 mm; the processed interference fringes are located in the range of interference fringe curves of the optimal OPD. By comparison with other current approaches, the suggested algorithm yields superior processing outcomes.

A Low-Latency Noise-Aware Tone Mapping Operator for Hardware Implementation with a Locally Weighted Guided Filter

A tone mapping operator (TMO) is a module in the image signal processing pipeline that is used to convert high dynamic range images to low dynamic range images for display. Currently, state-of-the-art TMOs typically take complex algorithms and are implemented on graphics processing units, making it difficult to run with low latency on edge devices, and TMOs implemented in hardware circuits often lack additional noise suppression because of latency and hardware resource constraints. To address these issues, we proposed a low-latency noise-aware TMO for hardware implementation. Firstly, a locally weighted guided filter is proposed to decompose the luminance image into a base layer and a detail layer, with the weight function symmetric concerning the central pixel value of a window. Secondly, the mean and standard deviation of the basic layer and the detail layer are used to estimate the noise visibility according to the human visual characteristics. Finally, the gain for the detail layer is calculated to achieve adaptive noise suppression. In this process, luminance is first processed by the log2 function before being filtered and then symmetrically converted back to the linear domain by the exp2 function after compression. Meanwhile, the algorithms within the proposed TMO were optimized for hardware implementation to minimize latency and cache, achieving a low latency of 60.32 μs under video specification of 1080 P at 60 frames per second and objective metric smoothness in dark flat regions could be improved by more than 10% compared to similar methods.

Steering Kernel Weighted Guided Image Filtering with Gradient Constraint

In order to make the weighted guided image filter (WGIF) more fully utilize the edge direction of the image, a steering kernel weighted guided image filter (SKWGIF) is proposed by employing the steering kernel to learn the edge direction and incorporating the learning results into the WGIF. However, SKWGIF does not provide a good compromise between the two possibly contradictory objectives of edge-preserving and smoothing, where the image edges are inevitably smoothed. To overcome the drawback, a SKWGIF with gradient constraint (GC-SKWGIF) is proposed by introducing the gradient constraints into the SKWGIF. The gradient constraints allow the filter to take into account the gradient variation of the edges in the filtering process, and therefore the image edges can be better preserved. To verify the effectiveness of the proposed filter, the GC-SKWGIF is applied to edge-aware smoothing, tone mapping of high range dynamic images, image denoising and haze removal. Both theoretical analysis and experimental results show that the proposed filter can produce good resultant images.

Logarithmically Optimized Real-Time HDR Tone Mapping With Hardware Implementation

Logarithmically Optimized Real-Time HDR Tone Mapping With Hardware Implementation

Dynamic Range Compression of Infrared Images Based on Histogram Equalization with Edge Inversion

The problem of compression of the dynamic range of infrared images is considered. To improve the quality of tone mapping of infrared images when their dynamic range is compressed and to simplify the control over the reproduction characteristics of infrared images, a dynamic range conversion algorithm based on adaptive histogram equalization with edge inversion is proposed. The essence of the algorithm consists in double reduction of the dynamic range of the infrared image with intermediate stretching, compression and overlapping of edges with inversion. To select the brightness interval and the degree of its stretching, the proposed algorithm uses the asymmetry coefficient. The algorithm makes it possible to improve some global and interval indicators of image reproduction quality by superimposing the edges of the histogram.

Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning

Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning