LEGION: Learning to Ground and Explain for Synthetic Image Detection

• URL: http://arxiv.org/abs/2503.15264v1
• Date: Wed, 19 Mar 2025 14:37:21 GMT
• Title: LEGION: Learning to Ground and Explain for Synthetic Image Detection
• Authors: Hengrui Kang, Siwei Wen, Zichen Wen, Junyan Ye, Weijia Li, Peilin Feng, Baichuan Zhou, Bin Wang, Dahua Lin, Linfeng Zhang, Conghui He,
• Abstract summary: We introduce SynthScars, a high-quality and diverse dataset consisting of 12,236 fully synthetic images with human-expert annotations.<n>It features 4 distinct image content types, 3 categories of artifacts, and fine-grained annotations covering pixel-level segmentation, detailed textual explanations, and artifact category labels.<n>We propose LEGION, a multimodal large language model (MLLM)-based image forgery analysis framework that integrates artifact detection, segmentation, and explanation.
• Score: 49.958951540410816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid advancements in generative technology have emerged as a double-edged sword. While offering powerful tools that enhance convenience, they also pose significant social concerns. As defenders, current synthetic image detection methods often lack artifact-level textual interpretability and are overly focused on image manipulation detection, and current datasets usually suffer from outdated generators and a lack of fine-grained annotations. In this paper, we introduce SynthScars, a high-quality and diverse dataset consisting of 12,236 fully synthetic images with human-expert annotations. It features 4 distinct image content types, 3 categories of artifacts, and fine-grained annotations covering pixel-level segmentation, detailed textual explanations, and artifact category labels. Furthermore, we propose LEGION (LEarning to Ground and explain for Synthetic Image detectiON), a multimodal large language model (MLLM)-based image forgery analysis framework that integrates artifact detection, segmentation, and explanation. Building upon this capability, we further explore LEGION as a controller, integrating it into image refinement pipelines to guide the generation of higher-quality and more realistic images. Extensive experiments show that LEGION outperforms existing methods across multiple benchmarks, particularly surpassing the second-best traditional expert on SynthScars by 3.31% in mIoU and 7.75% in F1 score. Moreover, the refined images generated under its guidance exhibit stronger alignment with human preferences. The code, model, and dataset will be released.

Related papers

• Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting [0.0]
  This study proposes a new sonar image synthesis framework, Synth-SONAR. The key novelties are threefold: First, by integrating Generative AI-based style injection techniques along with publicly available real/simulated data. Second, a dual text-conditioning sonar diffusion model hierarchy synthesizes coarse and fine-grained sonar images with enhanced quality and diversity. Third, high-level (coarse) and low-level (detailed) text-based sonar generation methods leverage advanced semantic information available in visual language models (VLMs) and GPT-prompting.
  arXiv  Detail & Related papers  (2024-10-11T08:27:25Z)
• Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective [45.210030086193775]
  Current synthetic image detection (SID) pipelines are primarily dedicated to crafting universal artifact features.<n>We propose SAFE, a lightweight and effective detector with three simple image transformations.<n>Our pipeline achieves a new state-of-the-art performance, with remarkable improvements of 4.5% in accuracy and 2.9% in average precision against existing methods.
  arXiv  Detail & Related papers  (2024-08-13T09:01:12Z)
• SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model [15.616316848126642]
  We develop a comprehensive artifact taxonomy and construct a dataset of synthetic images with artifact annotations for fine-tuning Vision-Language Model (VLM) The fine-tuned VLM exhibits superior ability of identifying artifacts and outperforms the baseline by 25.66%.
  arXiv  Detail & Related papers  (2024-02-28T05:54:02Z)
• HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View [67.8213192993001]
  We present HawkI, for synthesizing aerial-view images from text and an exemplar image. HawkI blends the visual features from the input image within a pretrained text-to-2Dimage stable diffusion model. At inference, HawkI employs a unique mutual information guidance formulation to steer the generated image towards faithfully replicating the semantic details of the input-image.
  arXiv  Detail & Related papers  (2023-11-27T01:41:25Z)
• Generalizable Synthetic Image Detection via Language-guided Contrastive Learning [22.4158195581231]
  malevolent use of synthetic images, such as the dissemination of fake news or the creation of fake profiles, raises significant concerns regarding the authenticity of images. We propose a simple yet very effective synthetic image detection method via a language-guided contrastive learning and a new formulation of the detection problem. It is shown that our proposed LanguAge-guided SynThEsis Detection (LASTED) model achieves much improved generalizability to unseen image generation models.
  arXiv  Detail & Related papers  (2023-05-23T08:13:27Z)
• 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)
• Re-Imagen: Retrieval-Augmented Text-to-Image Generator [58.60472701831404]
  Retrieval-Augmented Text-to-Image Generator (Re-Imagen) Retrieval-Augmented Text-to-Image Generator (Re-Imagen)
  arXiv  Detail & Related papers  (2022-09-29T00:57:28Z)
• Aggregated Contextual Transformations for High-Resolution Image Inpainting [57.241749273816374]
  We propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN) for high-resolution image inpainting. To enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block. For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task.
  arXiv  Detail & Related papers  (2021-04-03T15:50:17Z)
• You Only Need Adversarial Supervision for Semantic Image Synthesis [84.83711654797342]
  We propose a novel, simplified GAN model, which needs only adversarial supervision to achieve high quality results. We show that images synthesized by our model are more diverse and follow the color and texture of real images more closely.
  arXiv  Detail & Related papers  (2020-12-08T23:00:48Z)

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.