color correction

研究开发了一种开源颜色分级工具，并使用K-最近邻算法来预测色调区域阈值，以实现更有效的图像增强。

Existing spectral response modeling for digital cameras is typically confined to isolated components, lacking an end-to-end, physically consistent description from illumination input to pixel intensity output—thus limiting color fidelity and spectral accuracy. This paper introduces the first full-chain, physics-driven end-to-end spectral–color joint modeling framework. It unifies the coupled effects of optical system transmission, sensor quantum efficiency, color filter array (CFA) spectral transmittance, and nonlinear pixel response. The model integrates empirically measured RGB camera spectral responses with data-driven nonlinear mapping correction. Evaluated under multiple illuminants, it achieves superior color reproduction (mean ΔE < 1.2) and significantly improved spectral reconstruction fidelity (37% reduction in RMSE). Validated across machine vision, remote sensing, and computational spectral imaging applications, this work bridges a critical theoretical and practical gap in end-to-end camera spectral response modeling.

This study addresses the degradation of realism and emergence of skin tone bias in virtual human generation caused by the absence of chromatic calibration, which leads to skin color distortion. To tackle this issue, the authors propose the first fully automatic and scalable framework for skin tone fidelity evaluation. The framework integrates decoupling of skin tone and illumination, texture recoloring, real-time rendering, and quantitative analysis using ΔE and Individual Typology Angle (ITA) metrics in CIELAB color space. By incorporating TRUST-based illumination compensation and MetaHuman multi-illumination configurations, the system enables low-overhead, end-to-end assessment. Evaluation across 19,848 rendered instances reveals significant systematic chromatic bias against individuals with darker skin tones, and differential responses across phenotypes empirically confirm the presence of skin tone bias in current methods.

To address systematic color bias and high-frequency texture blurring in the DDColor model—caused by insufficient frequency-domain modeling and constrained input dimensionality—this paper proposes a dual-reconstruction framework jointly optimizing color fidelity and frequency representation. Methodologically, we introduce a lightweight color correction module and a learnable frequency compensation mechanism to collaboratively enhance chromatic accuracy and high-frequency detail recovery. Furthermore, we integrate RGB-YUV space mapping, frequency-domain feature disentanglement, and backbone network fine-tuning to enable multi-scale feature co-optimization. Experimental results demonstrate that our approach significantly outperforms the original DDColor model in both PSNR and SSIM metrics. Qualitatively, colorimetric fidelity and structural sharpness are substantially improved, effectively mitigating the model’s inherent chromatic biases and texture degradation.

Existing image recoloring and editing methods struggle to simultaneously achieve precise local color control, faithful texture preservation, and consistent color reproduction across luminance-varying regions. To address this, we propose a diffusion-based, quantized palette-driven editing framework. Our method uniquely employs quantized images as direct inputs to the diffusion model, enhancing interpretability and controllability. We design a weighted bipartite graph matching algorithm to enable semantically coherent, extreme palette transfer. Furthermore, we introduce multi-scale texture conditioning—optimized via thresholded gradient guidance—and JPEG-noise-robust training, overcoming the brightness-invariance limitation inherent in prior approaches. Extensive experiments demonstrate state-of-the-art performance: high-fidelity reconstruction, strict adherence to target palettes, and superior texture consistency. The framework supports both localized recoloring with fine-grained control and end-to-end palette migration, establishing a new benchmark for controllable, photorealistic image editing.

This work addresses the limitations of conventional image colorization methods, which operate in Lab space with a fixed luminance channel and thus struggle with non-standard grayscale inputs—such as orthochromatic photographs—and cannot adjust brightness. To overcome this, the authors propose a luminance-agnostic colorization framework that treats colorization as a full RGB image editing task. They introduce a hybrid grayscale training objective that uniformly accommodates both modern panchromatic and historical orthochromatic photographic inputs. By removing the fixed-luminance constraint, the method significantly enhances robustness to unnatural grayscale images. Experiments demonstrate superior performance on COCO, ImageNet, and multi-instance benchmarks, with markedly reduced color artifacts on orthochromatic images. Human evaluations confirm that the visual quality of the results substantially surpasses that of existing approaches.

This work addresses the common issue of color, brightness, and contrast distortion in smartphone photography and display, which arises from independent calibration of cameras and screens. To overcome this, the authors propose Color Pass-Through, the first end-to-end learning framework that treats the camera–display pipeline as a coupled system, enabling joint optimization of full-chain color fidelity directly on captured images. By bypassing traditional stage-wise calibration, the method avoids information bottlenecks and error accumulation, while supporting efficient, one-step calibration tailored to diverse observers. User studies demonstrate that the approach significantly enhances perceptual color reproduction, yielding an average improvement of 2.0 points on a 5-point subjective rating scale and more than doubling key objective metrics compared to existing solutions.

This work addresses the challenge of achieving perceptually accurate color reproduction in holographic displays, which is hindered by laser coherence, imperfections in spatial light modulators, chromatic aberrations, and camera color inaccuracies. To overcome these limitations, the authors propose the first perception-driven color management framework that integrates physical optical modeling with neural perceptual modeling. The framework jointly corrects input–output color inconsistencies through a pipeline comprising color space transformation, adaptive laser illumination control, and a neural network that models the camera’s color response. Comprehensive evaluations—including numerical simulations, optical experiments, and user studies—demonstrate significant improvements in color perceptual fidelity. This approach establishes a foundational step toward perception-driven holographic rendering.

This work addresses the evaluation gap between visual realism and verifiability in fine-grained image editing, as well as the subjective uncertainty inherent in human or VLM-based assessments. To this end, it introduces VeriEdit-Bench, the first deterministic evaluation benchmark grounded in structured asset source code. Methodologically, SVG source code is leveraged to control the editing process, generating precise targets and pixel-level masks that enable quantitative evaluation across four axes, including fidelity and preservation rate. This benchmark eliminates subjective bias by providing a fully reproducible scoring mechanism. Furthermore, it reveals significant performance disparities among existing models across multiple dimensions, cross-scenario ranking inversions, and distinct capability failure modes.

This work addresses the limitations of existing color spaces in accurately modeling human perceptual sensitivity to color differences in UI design, particularly in scenarios such as color palette generation, design token derivation, and light/dark mode adaptation, where high-precision, reversible, and engineering-friendly solutions are lacking. The authors propose HELMLAB—a 72-parameter analytical color space that uniquely integrates Fourier-based hue correction and the Helmholtz–Kohlrausch luminance effect into a fully invertible transformation. It enforces strict neutrality at a = b = 0 and employs a rigid rotation to preserve hue alignment and perceptual uniformity. Evaluated on the COMBVD dataset, HELMLAB achieves a STRESS value of 23.22—20.4% lower than CIEDE2000—with round-trip errors below 10⁻¹⁴. The framework is accompanied by practical tools for gamut mapping, design token export, and adaptive light/dark mode conversion.