Fact-checked by Grok 2 weeks ago

Tone mapping

Tone mapping is the process of compressing the of a () scene or image into the limited range of a low dynamic range (LDR) display while preserving visual quality as much as possible. This technique addresses the disparity between the wide range captured in HDR content—often spanning several orders of magnitude, from 10^{-6} to 10^8 cd/m², akin to the visual system's capabilities—and the narrower of typical devices. Originating in the early with advancements in rendering, tone mapping has evolved to enable photorealistic visualization in by simulating perceptual adaptation to light and contrast. In and image processing, tone mapping plays a critical role in applications such as , , and real-time rendering for and simulations. It transforms scene-referred signals, which represent absolute world luminances, into display-referred formats suitable for output devices with constrained and color gamut. For instance, in interactive environments like walkthroughs or driving simulators, tone mapping enhances immersion by accounting for visual adaptation processes, including light adaptation (over seconds) and dark adaptation (over minutes), to mimic how the eye adjusts to varying illumination. The technique is particularly vital for video, where it must maintain temporal across frames to prevent artifacts like flickering or ghosting, ensuring smooth playback on standard screens. Tone mapping operators (TMOs) are broadly categorized into global and local methods, with further subdivisions based on tone curves (e.g., linear, logarithmic, , or histogram-based), processing scope, and computational speed (offline, interactive, or real-time). Global TMOs apply a uniform mapping across the entire image for simplicity and efficiency, while local TMOs adjust contrast spatially using techniques like bilateral filtering or gradient-domain processing to better preserve details in both bright and dark regions. Notable examples include the photographic TMO, which emulates film-like responses, and noise-aware TMOs that handle sensor noise in captured content. These operators often incorporate models of human vision, such as multi-pass rendering to estimate average before applying adaptation-based adjustments. Since the , research has advanced TMOs to address challenges like computational demands for applications and perceptual , with over three decades of development leading to state-of-the-art methods that produce high-quality results for both images and video. Early work focused on static images in rendering pipelines, but by the 2010s, emphasis shifted to video-specific issues, including and exposure control, driven by improved capture technologies. Recent advances (2020–2025) incorporate for improved perceptual quality and inverse tone mapping for LDR-to-HDR expansion. Ongoing innovations continue to refine TMOs for emerging displays with expanded dynamic ranges, prioritizing metrics like temporal stability and subjective preference in evaluations.

Fundamentals

Definition and Principles

Tone mapping is a technique in image processing and computer graphics that compresses the wide range of luminance values in a high dynamic range (HDR) scene—typically spanning contrasts of up to 10^6:1 or more—to fit the limited dynamic range of standard displays, which often handle only about 100:1 to 1000:1, while avoiding clipping in highlights or loss of detail in shadows. This process ensures that the reproduced image maintains perceptual fidelity to the original scene as perceived by the human eye, by mapping scene luminances to display-adapted luminances without introducing artifacts like halos or washed-out colors. The key principles of tone mapping are rooted in the adaptation mechanisms of the human visual system (HVS), which dynamically adjusts sensitivity to light levels across a vast range, from 10^{-6} cd/m² in dim moonlight to 10^9 cd/m² in direct . Central to this is Weber's law, which states that the in (ΔL) is proportional to the background (L_b), expressed as ΔL / L_b ≈ constant (typically around 0.01 to 0.02), allowing the HVS to perceive relative contrasts consistently despite absolute intensity changes. Tone mapping applies compression to replicate this adaptation, scaling intensities logarithmically or via power functions to preserve local contrasts and overall appearance, while ideally leaving color reproduction unchanged by operating primarily in channels before reconverting to RGB. A basic form of tone mapping is the linear , defined as T(L) = a L + b, where L is the input scene , a is a scaling factor to fit the scene's range within the display's (e.g., 0 to 1 or 0 to 255), and b provides an offset for adjustment, often set to 0 for simplicity. This equation derives from the need to constrain output values to the display's physical limits, such as maximum and , ensuring no overflow while maintaining proportional relationships in mid-tones; however, it may require clipping (e.g., T(L) = \min(\max(a L + b, 0), L_{\max})) to handle extremes. Perceptually, tone mapping motivates the simulation of the eye's nonlinear response to , drawing from models like the Michaelis-Menten equation for photoreceptor , to produce images that appear natural and consistent with human brightness perception rather than raw photometric accuracy. By prioritizing differences over absolute values, as dictated by HVS adaptation, the technique enhances viewer immersion without the distortions seen in naive scaling or truncation.

Historical Development

The development of tone mapping began in the field of during the late 1980s and early 1990s, as researchers sought methods to reproduce realistic images from (HDR) scene data on low displays. Early efforts focused on perceptually based approaches that accounted for human vision models to compress without losing essential details. A seminal contribution came from Jack Tumblin and Holly Rushmeier, who in 1993 introduced a tone reproduction framework that matched display luminances to perceived brightness levels, drawing on psychophysical principles to ensure realism in rendered images. This work, published in IEEE Computer Graphics and Applications, formalized tone mapping as a distinct process in graphics pipelines and laid the groundwork for subsequent algorithms. The 1990s marked the emergence of imaging techniques, which necessitated advanced tone mapping to handle captured real-world radiance data. and Jitendra Malik's 1997 paper demonstrated the recovery of radiance maps from sequences of standard photographs, using bracketed exposures to estimate scene luminances exceeding display capabilities. This innovation, often referred to as the light probe technique, enabled and realistic scene relighting, spurring demand for effective tone operators to visualize such data. By the 2000s, tone mapping algorithms proliferated, with Erik Reinhard and colleagues' 2002 paper on photographic tone reproduction introducing a global operator inspired by traditional film processing, which adaptively scaled luminances to preserve photographic aesthetics across diverse scenes. These developments were prominently featured at conferences like , where dozens of tone mapping operators were presented, ranging from histogram-based to gradient domain methods, reflecting the field's rapid maturation. In the , tone mapping evolved toward applications, driven by hardware advances in capture and display technologies. Researchers optimized operators for efficiency, enabling integration into consumer devices such as smartphones and televisions; for instance, Apple's introduced HDR photography in 2010, relying on tone mapping to merge exposures on-device. This era saw a shift from offline rendering to interactive pipelines, with papers emphasizing low- global and local operators suitable for video streams. Post-2020, has transformed tone mapping, particularly for mobile HDR workflows, where neural networks learn adaptive curves from data to outperform traditional methods in detail preservation and artifact reduction. Notable examples include deep learning-based operators presented at NeurIPS, such as scene-adaptive models that process automotive HDR scenes with minimal . These AI-assisted techniques, often leveraging convolutional networks, have expanded tone mapping's accessibility in environments.

Techniques

Global Operators

Global operators in tone mapping apply a single uniformly to all pixels in an , compressing the based on aggregate statistics such as the mean luminance. This approach ensures consistent adjustment across the entire scene without considering local variations, making it fundamentally different from spatially adaptive methods. A foundational example is the Reinhard operator, developed in 2002 and inspired by the characteristics of , particularly the used in traditional photography to balance . The operator first computes the geometric mean luminance \bar{L}_w, scales the input world luminance L_w to L = a \bar{L}_w L_w where a is an exposure key value (typically 0.18), and then applies the mapping T(L) = \frac{L}{1 + L}, providing a simple yet effective global compression that mimics film's S-shaped response curve. Another key global operator is the Drago logarithmic mapping, introduced in 2003, which employs logarithmic compression to handle extreme dynamic ranges by attenuating high s more aggressively. Its core formula is T(L) = \frac{\log(L + 1)}{\log(L_{\max} + 1)} \times b, with b as an adjustable bias parameter (typically between 0.5 and 1.0) that controls the overall brightness while preserving perceptual uniformity. The mathematical foundations of operators often involve -based scaling, where the of the image informs a to stretch or compress tones proportionally, ensuring the output utilizes the full display without clipping details. These methods excel in computational efficiency, allowing processing on standard hardware due to their avoidance of per-pixel neighborhood computations. However, in high-contrast scenes—such as those with bright highlights against dark backgrounds— operators can produce undesirable artifacts around edges, as the uniform function fails to preserve local contrast transitions. Post-2020 advancements have extended logarithmic operators to video, incorporating automatic adjustment of the logarithmic base across frames to mitigate temporal inconsistencies like while maintaining contrast. For instance, a method dynamically computes the base from frame statistics, enabling seamless application in video pipelines.

Local Operators

Local operators in tone mapping adjust values based on of image regions, allowing the mapping function to vary per or localized area rather than applying a across the entire image. This approach leverages edge-preserving filters and other spatial techniques to compress high-dynamic-range () content while maintaining details in both bright and dark areas, effectively handling scenes with extreme local contrasts that methods might oversimplify. A seminal example is the bilateral filter-based method proposed by Durand and Dorsey, which decomposes the image into a large-scale base layer capturing overall illumination and a small-scale detail layer preserving edges and textures. The base layer undergoes logarithmic compression to fit within display limits, while the detail layer is added back with minimal alteration, resulting in enhanced local contrast without introducing artifacts like halos around bright objects. This technique, computationally efficient for real-time applications, has been widely adopted in image processing pipelines due to its simplicity and effectiveness in natural scenes. Another influential local operator is Fattal's gradient domain approach, which attenuates high-magnitude gradients in the image to reduce contrast while preserving low-magnitude ones for detail retention. The tone-mapped image L is obtained by solving the Poisson equation \nabla^2 L = \text{div}(t(\nabla I)), where I is the input HDR luminance, \nabla denotes the , \text{div} is the , and t is a scaling function that compresses large gradients. This method excels in rendering intricate details under varying lighting but requires iterative solvers, making it more resource-intensive than filter-based alternatives. Local operators offer advantages such as superior preservation of local contrast and reduction of halo artifacts compared to global techniques, enabling more natural-looking results in complex scenes. However, they often incur higher computational costs due to spatial processing and can introduce over-sharpening in textured regions if parameters are not tuned carefully. Implementation of local operators frequently involves multi-scale , such as using a Gaussian pyramid to separate frequency bands and apply region-specific compressions at each level, which helps manage intra-region variations effectively. Recent advancements in edge-aware filters have optimized these processes; for instance, developments in adaptive bilateral filtering integrate to achieve performance while minimizing gradient reversal artifacts. These updates address limitations in older implementations by incorporating learning-based for more precise local adaptations.

Hybrid and Advanced Methods

Hybrid and advanced methods in tone mapping integrate elements from and operators or leverage to enhance while preserving perceptual quality. These approaches address limitations of standalone techniques by combining uniform scene adjustments with spatially varying adaptations, or by learning mappings from data-driven models trained on (HDR) to low dynamic range (LDR) image pairs. For instance, hybrid operators merge luminance scaling with contrast enhancements to avoid artifacts like haloing in bright regions while maintaining computational efficiency. A seminal example is the Reinhard photographic tone reproduction operator, which applies a global sigmoidal curve inspired by response and incorporates local dodging-and-burning adjustments to simulate selective in dark and bright areas, thereby balancing overall with regional recovery. Another foundational is the adaptive logarithmic mapping, which uses a logarithmic function with spatially adaptive parameters to handle high-contrast scenes, ensuring visibility across levels without excessive loss in shadows or highlights. In recent years, has introduced advanced neural operators for tone mapping, such as region-adaptive self-supervised , which achieves superior perceptual uniformity by optimizing against human vision models during training on diverse HDR-LDR datasets. Such hybrid and neural techniques offer advantages in balancing processing speed and output quality, often outperforming traditional operators in subjective evaluations by reducing distortions while enabling applications. Recent trends emphasize GPU-accelerated implementations, such as differential zone mixing of multiple operators on graphics hardware, which supports interactive rendering at over 60 frames per second for high-resolution HDR video.

Applications

Digital Photography

In digital photography, tone mapping plays a crucial role in transforming (HDR) captures into viewable images suitable for print or web display. The process typically begins with bracketed exposures—multiple shots of the same scene at varying shutter speeds, such as -2, 0, and +2 —to capture details in shadows, midtones, and highlights beyond a single sensor's capabilities. These exposures are merged into an HDR radiance map, a linear representation of scene , using software that estimates camera response functions to align and combine values accurately. For instance, Photoshop's Merge to HDR Pro automates this fusion into a 32-bit floating-point image, followed by tone mapping to compress the while preserving perceptual details through methods like local , which simulates by adjusting regionally. Merging bracketed exposures presents challenges, particularly sensor noise amplified in underexposed shadow areas, where low photon counts lead to higher signal-to-noise ratios when details are recovered, and ghosting artifacts from subject or camera motion across frames, which misaligns content during fusion. These issues degrade image quality, with noise appearing as grainy textures in dark regions and ghosting creating blurred or duplicated elements in dynamic scenes. To mitigate them, exposure fusion techniques directly blend the bracketed images into a single standard dynamic range (SDR) output, weighting pixels based on quality metrics like saturation, exposure, and contrast without generating an intermediate HDR map, thereby reducing both noise and ghosting for more robust results in handheld photography. This approach, introduced in seminal work by Mertens et al., prioritizes perceptual quality over absolute radiance accuracy and is implemented in tools like Luminance HDR. Standards for HDR metadata in digital photography include extensions to the Exchangeable Image File Format (), where cameras embed tags indicating HDR processing, such as Apple's iOS-specific values for HDR modes (e.g., 2 for HDR without original saved), though full remains vendor-dependent via MakerNotes. The evolution toward smartphone has integrated on-device tone mapping, exemplified by Google Pixel's HDR+ pipeline in the 2024 Pixel 9 series, which processes bursts of raw frames through , denoising, and AI-driven tone mapping to produce SDR outputs directly on the device, enhancing efficiency for mobile workflows. Effective tone mapping in these pipelines yields outcomes like natural tones through accurate color rendering and balanced skies by compressing highlight without clipping, avoiding the unnatural halos or flattened contrasts seen in unprocessed . Post-2020 advancements in mobile AI, such as Pixel's refreshed + imaging, further refine these results by leveraging for selective detail enhancement, ensuring photorealistic images even in mixed lighting.

Display Devices

Display devices vary significantly in their dynamic range capabilities, necessitating tone mapping to adapt (HDR) content for optimal reproduction. Traditional (CRT) displays, which dominated early and computer monitors, offered limited dynamic ranges typically below 100:1 contrast ratios and peak brightness around 100-200 cd/m², constraining the rendering of details in both shadows and highlights. In contrast, modern organic light-emitting diode (OLED) televisions in 2025 achieve peak brightness exceeding 1000 nits for small highlight areas, enabling much wider dynamic ranges up to 1,000,000:1, though sustained full-screen brightness remains lower at around 250 nits to manage power and prevent . This evolution requires tone mapping operators to compress or expand signals to match device constraints, preserving perceptual fidelity as outlined in fundamental mapping principles. Metadata-driven tone mapping enhances adaptation for these displays by embedding scene-specific information in the signal. For instance, HDR10+ employs dynamic metadata to adjust tone mapping on a scene-by-scene or frame-by-frame basis, allowing displays to optimize brightness and contrast without static assumptions about content. Similarly, utilizes the (PQ) electro-optical transfer function (EOTF) as defined in SMPTE ST 2084, which maps normalized code values to levels up to 10,000 cd/ using a specific non-linear curve based on human , enabling precise mapping from code values to absolute . Automatic techniques, such as those in HDR10+, analyze content in real-time for broad compatibility, while manual methods in professional workflows allow creators to define custom curves for specific displays, balancing automation with artistic intent. Challenges in tone mapping for displays include black level crushing, where low-luminance details are lost due to insufficient , and color shifts arising from independent adjustments in one-dimensional lookup tables (LUTs). These issues are particularly pronounced in OLEDs during playback, as aggressive compression can alter hue ratios and clip shadow information. Solutions incorporate standardized tone mapping curves in broadcast protocols, such as those recommended in BT.2390, which provide sample mappings for displays with s as low as 0.1 cd/m² and white levels up to 1000 cd/m², ensuring consistent reproduction across transmission chains. Recent advances in 2025, including micro-LED displays with peak brightness surpassing 4000 nits and near-perfect blacks, introduce the need for tone mapping to upscale legacy low (LDR) content for these high-fidelity panels. Unlike earlier LCD-focused approaches, micro-LED's expanded capabilities demand algorithms that expand rather than compress , as explored in ongoing research challenges on tone mapping to enhance visibility without introducing artifacts.

Computer Graphics and Video Rendering

In , tone mapping is integrated into rendering pipelines to compress () scene data generated from physically-based into low dynamic range (LDR) outputs suitable for display. This process typically occurs as a post-shading step after calculations and before final , ensuring that synthetic images retain perceptual realism while fitting display constraints. For instance, in 5, the filmic tonemapper applies a non-linear curve to HDR color data in the post-process volume, simulating photographic and for physically-based rendered scenes. For video rendering, maintaining frame-consistent tone mapping is essential to prevent temporal artifacts like , which arise from varying mappings across frames. Techniques such as adaptive temporal filtering adjust the tone curve based on scene motion and global statistics, enforcing by propagating parameters from previous frames while adapting to content changes. In broadcast video production, the Hybrid Log-Gamma (HLG) standard facilitates backward-compatible tone mapping, encoding signals in a single stream that renders as SDR on legacy devices or enhanced on compatible ones, as defined in BT.2100. Real-time applications in gaming leverage hardware-accelerated tone mapping for ray-traced scenes, enabling immersive visuals at interactive frame rates. NVIDIA's RTX technologies, updated in 2024 with DLSS 3.5, incorporate tone mapping within ray reconstruction pipelines to denoise and map ray-traced lighting data efficiently, as seen in titles like Complete Edition supporting full ray tracing. In film (VFX), the Academy Color Encoding System (ACES) workflow employs Input Device Transforms () to linearize scene-referred data and Output Device Transforms (ODT) combined with the Reference Rendering Transform (RRT) for tone mapping, ensuring consistent color across compositing tools like Nuke and rendering in . Key challenges in these domains include achieving temporal coherence amid dynamic lighting and camera movement, often addressed through hybrid methods that blend global and operators for stability. Recent research, such as foveated methods proposed in , explores applying higher-fidelity compression only in the user's gaze region for / headsets to optimize performance on edge devices while leveraging visual attention models.

Examples and Processes

Imaging Pipeline Overview

The (HDR) imaging pipeline encompasses a sequence of stages designed to capture, process, and display scenes with luminance ranges exceeding those of conventional low dynamic range (LDR) devices, typically spanning 10-14 stops or more. It begins with scene capture, where specialized cameras acquire multiple LDR images at varying times to sample the full of the scene, often using bracketed exposures to avoid saturation in bright areas and underexposure in shadows. This step leverages sensor capabilities, such as those in multi-exposure HDR cameras, to gather raw data that encodes both high-intensity highlights and low-intensity details. Following capture, radiance map estimation reconstructs an HDR representation of the scene by merging the input images, estimating absolute values through techniques like weighted averaging or inverting the camera response function () to account for camera response functions. The resulting radiance map, often stored in formats like to preserve floating-point precision and linear light values, serves as the scene-referred input for subsequent processing. Next, tone mapping application compresses this wide range into an LDR format suitable for standard displays (e.g., 8-bit per channel), employing or operators to simulate human vision's adaptation while retaining contrast and detail. For instance, processing an input HDR image in format might involve applying a tone mapping operator (TM) pixel-wise, as in the following pseudocode:
for each pixel in image:
    L_out = TM(L_in)
where L_{in} is the input radiance and L_{out} is the compressed luminance, yielding an intermediate display-referred image. The pipeline then proceeds to gamut mapping and encoding, where colors are transformed and clipped to fit the target device's color volume, often involving CIEXYZ projections and perceptual uniform adjustments to handle chroma shifts introduced by tone mapping. This stage ensures compatibility with standards like sRGB, encoding the final LDR output for storage or transmission. A conceptual diagram of this pipeline would depict a linear flow from raw captures to encoded image, highlighting bottlenecks such as inverse tone mapping during editing, where LDR previews must be expanded back to HDR to enable non-destructive modifications without irreversible dynamic range loss. Overall, the end-to-end process provides holistic dynamic range reduction, preserving perceptual fidelity; for video extensions, it incorporates temporal processing across frames to maintain consistency and mitigate artifacts like flickering, adapting the core stages to sequential data.

Algorithmic Implementations

Implementing tone mapping algorithms requires careful consideration of computational efficiency, , and hardware constraints. A seminal global operator, the Reinhard photographic tone reproduction method, provides a straightforward starting point for practical implementations. This operator first computes the log-average \bar{L}_w across the image as \bar{L}_w = \exp\left(\frac{1}{N} \sum_{x,y} \log(\delta + L_w(x,y))\right), where N is the number of pixels, L_w(x,y) is the world at each pixel, and \delta is a small constant (e.g., $10^{-4}) to avoid log singularities. The is then scaled by a key value a (typically 0.18 for middle-gray scenes) to obtain L(x,y) = a \frac{L_w(x,y)}{\bar{L}_w}. Finally, the display is mapped as L_d(x,y) = \frac{L(x,y)}{1 + L(x,y)}, with an optional white-point adjustment L_d(x,y) = \frac{L(x,y) (1 + \frac{L(x,y)}{L_{white}^2})}{(1 + L(x,y)) (1 + \frac{L(x,y)}{L_{white}})} where L_{white} is the desired maximum display (e.g., 100 cd/m²). To normalize for display, the resulting RGB values are scaled by the maximum channel value and gamma-corrected (e.g., \gamma = 2.2). Pseudocode for the full Reinhard global operator with normalization is as follows:
function ReinhardGlobalToneMap(HDR_image, key=0.18, white=1.0, gamma=2.2):
    # Assume HDR_image is a floating-point RGB array [0, inf)
    # Compute luminance (simple weighted sum)
    L_w = 0.299 * R + 0.587 * G + 0.114 * B  # for each pixel
    
    # Log-average luminance
    log_sum = sum(log(max(epsilon, L_w))) / num_pixels
    L_bar = exp(log_sum)
    
    # Scale
    L = key * L_w / L_bar
    
    # Tone map
    if white > 0:
        L_d = L * (1 + L / white**2) / ((1 + L) * (1 + L / white))
    else:
        L_d = L / (1 + L)
    
    # Reconstruct RGB
    LDR = HDR_image * (L_d / L_w)  # Preserve ratios, handle L_w=0 edge case
    
    # Normalize to [0,1]
    max_val = max over all channels in LDR
    LDR = LDR / max_val
    
    # Gamma correction
    LDR = pow(LDR, 1/gamma)
    
    return clamp(LDR, 0, 1)
This implementation assumes linear RGB input and handles division-by-zero via epsilon. For local operators, the enables edge-preserving contrast reduction, as in Durand and Dorsey's method. The process decomposes the image into a large-scale base layer and a detail layer using an edge-stopping Gaussian kernel. First, compute per-pixel intensity I (e.g., I = 0.3R + 0.59G + 0.11B). Apply the to obtain the base layer B_s = \frac{1}{k(s)} \sum_{p} G_{\sigma_s}(\|p - s\|) G_{\sigma_r}(|I_p - I_s|) I_p, where G_{\sigma_s} is the spatial Gaussian ( \sigma_s \approx 2\% of image width), G_{\sigma_r} is the range Gaussian ( \sigma_r \approx 0.4), and k(s) is the normalization factor \sum_{p} G_{\sigma_s}(\|p - s\|) G_{\sigma_r}(|I_p - I_s|). The detail layer is then D = I / B. Compress the base layer's contrast in log space (e.g., B' = \log(B), scale by factor 0.2, then B'' = \exp(B')), and recompose as I' = B'' * D. Repeat for color channels using intensity ratios to avoid color shifts. Optimized implementations use separable convolutions or GPU acceleration to reduce the O(n^2) complexity. Several libraries facilitate tone mapping implementations. OpenCV's photo module includes the cv::TonemapReinhard , which applies the global operator with parameters for intensity scaling (default -1.0 for automatic), light adaptation (0.0-1.0, default 1.0), and color adaptation (0.0-1.0, default 0.6); usage involves creating a tonemap object, calling process() on an (32-bit float), and converting to 8-bit via convertTo(). MATLAB's Image Processing Toolbox provides the tonemap function, which renders using methods like 'reinhard' (global ), 'drago' (logarithmic), or 'local' (bilateral-based); for example, RGB = tonemap(HDR, 'Method', 'reinhard', 'KeyValue', 0.18) normalizes and gamma-corrects output to [0,1]. For real-time applications, GPU in GLSL enable efficient processing; a Reinhard fragment shader might sample , apply color = color / (1.0 + color), normalize by luminance max, and output gamma-corrected fragments. With browser support available since 2023 (e.g., 113 and later), WGSL shaders replace GLSL for cross-platform web rendering, maintaining similar compute pipelines for tone mapping. To assess implementation quality, the Tone-Mapped Image Quality Index (TMQI) combines a multi-scale structural fidelity measure (based on modified SSIM) with a naturalness metric evaluating intensity statistics against natural image distributions; higher TMQI scores (0-1 range) indicate better preservation of details and perceptual realism. Common pitfalls include overflow in floating-point computations during luminance scaling or filter summations, which can be mitigated by clamping inputs to [0, max_lum] (e.g., 10^5 cd/m²) and using half-precision floats on GPUs, or by iterative normalization in OpenCV's minMaxLoc to avoid location-return errors in bindings. Recent advancements integrate neural backends; for instance, the 2024 CATMO library in uses for contrastive learning-based deep tone mapping, optimizing end-to-end priors on datasets, while colour-hdri provides HDRI tools compatible with for custom neural extensions like histogram-guided networks.

References

  1. [1]
    [PDF] A comparative review of tone-mapping algorithms for high dynamic ...
    This report reviews tone-mapping for HDR video, summarizes research, and provides a comparison of state-of-the-art algorithms, including a list of 26 ...
  2. [2]
    [PDF] Interactive Tone Mapping - Computer Graphics Group
    Abstract. Tone mapping and visual adaptation are crucial for the generation of static, photorealistic images. A largely unexplored problem is the simulation ...<|control11|><|separator|>
  3. [3]
    [PDF] Tone Mapping
    • Arithmetic of HDR images. • The perception of HDR scenes. • Major approaches to tone-mapping. • Illumination & reflectance separation. • Forward visual model.
  4. [4]
    [PDF] Photographic tone reproduction for digital images
    Jan 14, 2002 · A classic photographic task is the mapping of the potentially high dynamic range of real world luminances to the low dynamic range of the ...
  5. [5]
    [PDF] The Human Visual System and HDR Tone Mapping
    Thus, Weber's law may be considered as a behavioral manifestation of photoreceptor adaptation. The preceding discussion of the various mechanisms of visual ...Missing: principles | Show results with:principles<|control11|><|separator|>
  6. [6]
    [PDF] Tone reproduction for realistic images
    Tone Reproduction for Realistic Images. Jack Tumblin and Holly Rushmeier. Georgia Institute of Technology. Display methods should compensate for all light ...Missing: seminal | Show results with:seminal
  7. [7]
    [PDF] Tone reproduction for realistic images - Semantic Scholar
    The main contributions of this thesis in tone mapping techniques are interactive calibration of contrast and aperture, minimum information loss methods and ...Missing: seminal | Show results with:seminal
  8. [8]
    Photographic tone reproduction for digital images
    A survey of tone mapping techniques. In 13th Spring Conference on Computer Graphics, W. Straßer, Ed., 163-170. Google Scholar. [24]. MCNAMARA, A., CHALMERS, A ...
  9. [9]
    Real-time Tone Mapping: A State of the Art Report - ResearchGate
    Mar 9, 2020 · In this we survey will discuss those tonemap algorithms which have been implemented on GPU [1-10], FPGA [11-41], and ASIC [42-53] in terms of ...
  10. [10]
    [PDF] Adaptive Logarithmic Mapping For Displaying High Contrast Scenes
    Abstract. We propose a fast, high quality tone mapping technique to display high contrast images on devices with limited dy- namic range of luminance values ...
  11. [11]
    [PDF] A Visibility Matching Tone Reproduction Operator for High Dynamic ...
    A tone-mapping operator proposed by Tumblin and. Rushmeier [21] concentrated on the problem of preserving the viewer's overall impression of brightness. As ...Missing: seminal | Show results with:seminal
  12. [12]
    [PDF] Video logarithmic tone mapping operator with automatic calculation ...
    May 24, 2022 · This paper describes a new method for a real time automatic calculation of the logarithmic function base, depending on the characteristics of ...
  13. [13]
    Perception Motivated Hybrid Approach to Tone Mapping
    Our approach is based on combination of arbitrary global and local tone mapping operators. Recent perceptual studies concerning the reproduction of HDR ...
  14. [14]
    Hybrid Conditional Deep Inverse Tone Mapping - ACM Digital Library
    Oct 10, 2022 · We propose a deep learning based SDR-to-HDR solution, Hybrid Conditional Deep Inverse Tone Mapping (HyCondITM), which is an end-to-end trainable ...
  15. [15]
    [PDF] Single-Image HDR Reconstruction by Learning to Reverse the ...
    We also evalu- ate the PSNR, SSIM, and perceptual score with the LPIPS metric [57] on the tone-mapped HDR images in the supple- mentary material. 4.2.
  16. [16]
    Tone mapping high dynamic range images based on region ...
    This paper presents a region-adaptive self-supervised deep learning (RASSDL) technique for high dynamic range (HDR) image tone mapping.
  17. [17]
    Mixing tone mapping operators on the GPU by differential zone ...
    We have presented a novel approach for tone mapping. Our work is an hybrid TMO which tackles the issue that existing TMOs do not achieve similar quality results ...
  18. [18]
    [PDF] Boosting Inverse Tone Mapping via Diffusion Regularization
    Jul 5, 2025 · In recent times, a multitude of approaches have emerged that leverage deep convolutional neural networks (CNNs) to address the task at hand.
  19. [19]
    High dynamic range images in Photoshop - Adobe Help Center
    May 24, 2023 · In Photoshop, the Merge To HDR Pro command lets you create HDR images by combining multiple photographs captured at different exposures.
  20. [20]
    [PDF] High dynamic range imaging and tonemapping
    Oct 9, 2017 · How would you merge the non-linear images into an HDR one? Exposure ... image to absolute radiance map. HDR image. (relative radiance).
  21. [21]
    [PDF] Noise-Optimal Capture for High Dynamic Range Photography
    Taking multiple exposures is a well-established approach both for capturing high dynamic range (HDR) scenes and for noise reduction. But what is the optimal ...
  22. [22]
    [PDF] Robust High Dynamic Range (HDR) Imaging with Complex Motion ...
    Thus, effectively removing artifacts caused by motion or parallax is the main challenge for high-quality, ghosting-free HDR imaging.
  23. [23]
    Exposure Fusion | IEEE Conference Publication
    Exposure Fusion. Abstract: We propose a technique for fusing a bracketed exposure sequence into a high quality image, without converting to HDR first.
  24. [24]
    EXIF Tags
    Sep 21, 2025 · (only 0 and 1 are standard EXIF, but other values are used by Apple iOS devices). 0 = Normal 1 = Custom 2 = HDR (no original saved) 3 = HDR ( ...
  25. [25]
    Google Pixel 9: New camera specs and AI photo features
    Aug 13, 2024 · Reflect what you see with a new HDR+ imaging pipeline. We've thoroughly updated our imaging pipeline for even better, more true-to-life photos.
  26. [26]
    Google Pixel 9 Camera test - DXOMARK
    Aug 20, 2024 · Google Pixel 9 – Pleasant color rendering, accurate skin tones. Google Pixel 8 – Pleasant color rendering but slightly unnatural skin tones.
  27. [27]
    HDR photo editing with machine learning - Google Research
    Oct 16, 2024 · Our new machine learning model unlocks high dynamic range (HDR) image editing in Google Photos, promoting standard dynamic range image pixels to HDR image ...
  28. [28]
    Color Grading and the Filmic Tonemapper in Unreal Engine
    The purpose of the Tone Mapping function is to map the wide range of high dynamic range (HDR) colors into low dynamic range (LDR) that a display can output.
  29. [29]
    [PDF] Temporal Coherency for Video Tone Mapping - l'IRISA
    While effectively reducing the flickering, these techniques do not solve all the problems inherent in video tone mapping such as the perception consistency of ...
  30. [30]
    Foveated HDR: Efficient HDR Content Generation on Edge Devices ...
    Apr 9, 2025 · We propose Foveated HDR for efficient HDR content generation on edge devices by leveraging the foveation nature of human vision system.
  31. [31]
    High Dynamic Range Spectral Imaging Pipeline For Multispectral ...
    Then, the HDR image may be used as is for machine vision, or it continues into a visualization pipeline, where color transform, tone-mapping and image- ...
  32. [32]
    Chapter 26. The OpenEXR Image File Format - NVIDIA Developer
    OpenEXR is a high-dynamic-range image file format developed by Industrial Light & Magic (ILM) for use in computer imaging applications.
  33. [33]
    Deep HDR Hallucination for Inverse Tone Mapping - PMC - NIH
    Jun 11, 2021 · Inverse Tone Mapping (ITM) methods attempt to reconstruct High Dynamic Range (HDR) information from Low Dynamic Range (LDR) image content.
  34. [34]
    cv::TonemapReinhard Class Reference - OpenCV Documentation
    This is a global tonemapping operator that models human visual system. Mapping function is controlled by adaptation parameter.
  35. [35]
    [PDF] Fast Bilateral Filtering for the Display of High-Dynamic-Range Images
    We build on bilateral filtering, a non-linear filter introduced by Tomasi et al. [1998]. It derives from Gaussian blur, but it prevents blurring across edges ...
  36. [36]
    High Dynamic Range Imaging - OpenCV Documentation
    After the HDR image has been blended it has to be converted back to 8-bit to view it on usual displays. This process is called tonemapping.
  37. [37]
    tonemap - Render high dynamic range image for viewing - MATLAB
    Tone mapping is a technique used to approximate the appearance of high dynamic range images on a display with a more limited dynamic range. RGB = tonemap( HDR , ...
  38. [38]
    What's New in WebGPU (Chrome 129) | Blog
    Sep 17, 2024 · The new GPUCanvasToneMappingMode parameter in the WebGPU canvas configuration now allows WebGPU to draw colors brighter than white.Missing: GLSL | Show results with:GLSL
  39. [39]
    dmnsgn/glsl-tone-map - GitHub
    A collection of tone mapping functions available both as ES modules strings and as GLSL files for use with glslify. Mostly taken from here and here.Missing: example | Show results with:example
  40. [40]
    TMQI: Tone Mapped Image Quality Index
    Oct 6, 2012 · TMQI is an objective quality assessment algorithm for tone mapped images by combining 1) a multi-scale signal fidelity measure based on a modified structural ...
  41. [41]
    python - Understanding OpenCV tonemapping implementation
    Jun 18, 2024 · The process() method asserts that the source image is a 3-channel 32-bit floating point matrix, then calls minMaxLoc with that image.HDR, adaptive tone mapping and MSAA in GLSL - Stack OverflowReinhard tone-mapping 2002 - algorithm - Stack OverflowMore results from stackoverflow.comMissing: pitfalls | Show results with:pitfalls
  42. [42]
    Tone Mapping HDR Luminance to an SDR-compatible Range
    Oct 9, 2025 · The following issues can occur with this implementation: Banding is caused when the render target used by GPU composition is of lower precision ...Missing: pitfalls | Show results with:pitfalls
  43. [43]
    [IMAGE24] Contrastive learning for deep tone mapping operator
    In this project, we present a straightforward yet efficient framework to automatically learn the priors and perform tone mapping in an end-to-end manner. The ...
  44. [44]
    colour-hdri - PyPI
    A Python package implementing various HDRI processing algorithms. It is open source and freely available under the BSD-3-Clause terms.Missing: neural TensorFlow<|control11|><|separator|>