Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images

• URL: http://arxiv.org/abs/2606.02224v2
• Date: Tue, 09 Jun 2026 12:14:34 GMT
• Title: Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images
• Abstract summary: We exploit an underexplored cue in current generative models, namely their weakness to imitate color statistics of natural images.<n>We introduce six hand-crafted color transformations and a method to learn a task-optimized color transform to statistically expose generated images.
• Score: 12.421358556104062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The evolution and dissemination of AI-synthesized images is occurring at an unprecedented rate. Image generators are making rapid progress in their goal of perfectly imitating natural images, which also challenges image forensics. In this work, we exploit an underexplored cue in current generative models, namely their weakness to imitate color statistics of natural images. We first show that the LPIPS loss used for training image generators is less sensitive to chrominance than to luminance, which may lead to statistical discrepancies in the colors of synthetic images. Building on this observation, we then introduce six hand-crafted color transformations and a method to learn a task-optimized color transform to statistically expose generated images. These transformations can be used in various ways. First, we define color-sensitive features at pixel-level or patch-level. A simple, interpretable classifier achieves with these features an average generalization accuracy of 93.27% and strong robustness against six types of post-processing. Second, we demonstrate that the transformations exhibit characteristic visual noise patterns in natural and synthetic image areas, which enables an intuitive visual image evaluation. Third, we demonstrate that the transforms can enhance color patterns in generated images for improved multiclass attribution.

Related papers

• Detecting Generated Images by Fitting Natural Image Distributions [75.31113784234877]
  We propose a novel framework that exploits geometric differences between the data manifold of natural and generated images.<n>We employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones.<n>An image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images.
  arXiv  Detail & Related papers  (2025-11-03T07:20:38Z)
• Transforming Color: A Novel Image Colorization Method [8.041659727964305]
  This paper introduces a novel method for image colorization that utilizes a color transformer and generative adversarial networks (GANs) The proposed method integrates a transformer architecture to capture global information and a GAN framework to improve visual quality. Experimental results show that the proposed network significantly outperforms other state-of-the-art colorization techniques.
  arXiv  Detail & Related papers  (2024-10-07T07:23:42Z)
• Incorporating Ensemble and Transfer Learning For An End-To-End Auto-Colorized Image Detection Model [0.0]
  This paper presents a novel approach that combines the advantages of transfer and ensemble learning approaches to help reduce training time and resource requirements. The proposed model shows promising results, with accuracy ranging from 94.55% to 99.13%.
  arXiv  Detail & Related papers  (2023-09-25T19:22:57Z)
• A Robust Image Forensic Framework Utilizing Multi-Colorspace Enriched Vision Transformer for Distinguishing Natural and Computer-Generated Images [0.0]
  We propose a robust forensic classifier framework leveraging enriched vision transformers to distinguish between natural and generated images. Our approach outperforms baselines, demonstrating 94.25% test accuracy with significant performance gains in individual class accuracies. This work advances the state-of-the-art in image forensics by providing a generalized and resilient solution to distinguish between natural and generated images.
  arXiv  Detail & Related papers  (2023-08-14T17:11:17Z)
• Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images [60.34381768479834]
  Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. We pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2023-04-02T10:25:09Z)
• Neural Color Operators for Sequential Image Retouching [62.99812889713773]
  We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. Our method consistently achieves the best results compared with SOTA methods in both quantitative measures and visual qualities.
  arXiv  Detail & Related papers  (2022-07-17T05:33:19Z)
• Detecting Recolored Image by Spatial Correlation [60.08643417333974]
  Image recoloring is an emerging editing technique that can manipulate the color values of an image to give it a new style. In this paper, we explore a solution from the perspective of the spatial correlation, which exhibits the generic detection capability for both conventional and deep learning-based recoloring. Our method achieves the state-of-the-art detection accuracy on multiple benchmark datasets and exhibits well generalization for unknown types of recoloring methods.
  arXiv  Detail & Related papers  (2022-04-23T01:54:06Z)
• Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations [0.9051352746190446]
  HistAuGAN can simulate a wide variety of realistic histology stain colors, thus making neural networks stain-invariant when applied during training. Based on a generative adversarial network (GAN) for image-to-image translation, our model disentangles the content of the image, i.e., the morphological tissue structure, from the stain color attributes. It can be trained on multiple domains and, therefore, learns to cover different stain colors as well as other domain-specific variations introduced in the slide preparation and imaging process.
  arXiv  Detail & Related papers  (2021-07-26T17:52:39Z)
• Texture for Colors: Natural Representations of Colors Using Variable Bit-Depth Textures [13.180922099929765]
  We present an automated method to transform an image to a set of binary textures that represent not only the intensities, but also the colors of the original. The system yields aesthetically pleasing binary images when tested on a variety of image sources.
  arXiv  Detail & Related papers  (2021-05-04T21:22:02Z)
• Ensembling with Deep Generative Views [72.70801582346344]
  generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose. Here, we investigate whether such views can be applied to real images to benefit downstream analysis tasks such as image classification. We use StyleGAN2 as the source of generative augmentations and investigate this setup on classification tasks involving facial attributes, cat faces, and cars.
  arXiv  Detail & Related papers  (2021-04-29T17:58:35Z)
• Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement [52.49231695707198]
  We investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps. Inspired by the color image formulation, we first estimate the degradation from low-light inputs to simulate the distortion of environment illumination color, and then refine the content to recover the loss of diffuse illumination color. Our proposed method has surpassed the SOTA by 0.95dB in PSNR on LOL1000 dataset and 3.18% in mAP on ExDark dataset.
  arXiv  Detail & Related papers  (2021-03-19T04:00:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.