Tone Mapping Research Articles

Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion

Image visibility is often degraded under challenging conditions such as low light, backlighting, and inadequate contrast. To mitigate these issues, techniques like histogram equalization, high dynamic range (HDR) tone mapping and near-infrared (NIR)–visible image fusion are widely employed. However, these methods have inherent drawbacks: histogram equalization frequently causes oversaturation and detail loss, while visible–NIR fusion requires complex and error-prone images. The proposed algorithm of a complementary cycle-consistent generative adversarial network (CycleGAN)-based training with visible and NIR images, leverages CycleGAN to generate fake NIR images by blending the characteristics of visible and NIR images. This approach presents tone compression and preserves fine details, effectively addressing the limitations of traditional methods. Experimental results demonstrate that the proposed method outperforms conventional algorithms, delivering superior quality and detail retention. This advancement holds substantial promise for applications where dependable image visibility is critical, such as autonomous driving and CCTV (Closed-Circuit Television) surveillance systems.

A novel deep unsupervised approach for super-resolution of remote sensing hyperspectral image using gompertz-function convergence war accelerometric-optimization generative adversarial network (GF-CWAO-GAN)

Hyperspectral remote sensing images obtained from cameras are characterized by high-dimensions and low quality, which makes them unfavorable for various analytics purposes. This is due to the presence of visible and invisible frequencies of the reflected light making it poorly reveal the spectral signatures of the image. Visual communication advancement has paved the need for Image Super-Resolution (SR) which recovers high-resolution images from low-resolution images. Several works were carried out earlier on image SR using variants of supervised and unsupervised models that still lack accuracy. In this paper, we propose an unsupervised learning model titled Gompertz Function–based Convergence War Accelerometric Optimization–GAN framework for generating of High-Resolution (HR) images. The framework comprises a pre-processing stage, where the incoming Low-Resolution (LR) image is preprocessed for noise removal by applying Shannon-Gaussian Filter (S-GF). Following is the Gradient Domain Approach based Tone-Mapping (TM). Skew correction is done to remove distortion and maintain original resolution that may change during TM stage. The next stage comprises the boundary and edge enhancement of the resulting preprocessed image generated by the method of Inverse Gradient Mapping (IGM) followed by patch extraction to extract minute low-frequency information from the resulting boundary and edge-enhanced image. The contrast of the enhanced patches is improved by removing blurriness effect. The preprocessed image patches are then fed into the Gompertz Function-based Convergence War Accelerometric Optimization – GAN for feature mapping on the trained SR Image features that are clustered using Krzanowski and Li- Kantorovich Metric-K-Means clustering Algorithm (KL-KM-KMA) for effective generation of SR image. The developed model is validated for both qualitative and quantitative measurements. Comparisons are made with several other state-of -the-art methods for accuracy of 98.05%, precision of 97.98%, inception score of 8.71, Fréchet Inception Distance of 36.4 with reduced clustering and training time proving the efficiency of the proposed model.

LTM-NeRF: Embedding 3D Local Tone Mapping in HDR Neural Radiance Field.

Recent advances in Neural Radiance Fields (NeRF) have provided a new geometric primitive for novel view synthesis. High Dynamic Range NeRF (HDR NeRF) can render novel views with a higher dynamic range. However, effectively displaying the scene contents of HDR NeRF on diverse devices with limited dynamic range poses a significant challenge. To address this, we present LTM-NeRF, a method designed to recover HDR NeRF and support 3D local tone mapping. LTM-NeRF allows for the synthesis of HDR views, tone-mapped views, and LDR views under different exposure settings, using only the multi-view multi-exposure LDR inputs for supervision. Specifically, we propose a differentiable Camera Response Function (CRF) module for HDR NeRF reconstruction, globally mapping the scene's HDR radiance to LDR pixels. Moreover, we introduce a Neural Exposure Field (NeEF) to represent the spatially varying exposure time of an HDR NeRF to achieve 3D local tone mapping, for compatibility with various displays. Comprehensive experiments demonstrate that our method can not only synthesize HDR views and exposure-varying LDR views accurately but also render locally tone-mapped views naturally.

XTC-DDPM: Diffusion Model for Tone Mapping and Pseudo-Color Imaging of Dual-Energy X-Ray Security Inspection Images

XTC-DDPM: Diffusion Model for Tone Mapping and Pseudo-Color Imaging of Dual-Energy X-Ray Security Inspection Images

Luminance decomposition and Transformer based no-reference tone-mapped image quality assessment

Tone-Mapping Operators (TMOs) play a crucial role in converting High Dynamic Range (HDR) images into Tone-Mapped Images (TMIs) with standard dynamic range for optimal display on standard monitors. Nevertheless, TMIs generated by distinct TMOs may exhibit diverse visual artifacts, highlighting the significance of TMI Quality Assessment (TMIQA) methods in predicting perceptual quality and guiding advancements in TMOs. Inspired by luminance decomposition and Transformer, a new no-reference TMIQA method based on deep learning is proposed in this paper, named LDT-TMIQA. Specifically, a TMI will change under the influence of different TMOs, potentially resulting in either over-exposure or under-exposure, leading to structure distortion and changes in texture details. Therefore, we first decompose the luminance channel of a TMI into a base layer and a detail layer that capture structure information and texture information, respectively. Then, they are employed with the TMI collectively as inputs to the Feature Extraction Module (FEM) to enhance the availability of prior information on luminance, structure, and texture. Additionally, the FEM incorporates the Cross Attention Prior Module (CAPM) to model the interdependencies among the base layer, detail layer, and TMI while employing the Iterative Attention Prior Module (IAPM) to extract multi-scale and multi-level visual features. Finally, a Feature Selection Fusion Module (FSFM) is proposed to obtain final effective features for predicting the quality scores of TMIs by reducing the weight of unnecessary features and fusing the features of different levels with equal importance. Extensive experiments on the publicly available TMI benchmark database indicate that the proposed LDT-TMIQA reaches the state-of-the-art level.

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.