As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a tendency towards overconfidence, leading to incorrect predictions; and difficulty in detecting subtle tampering boundaries in inpainted images. In response, we propose a new paradigm that treats IIL as a conditional mask generation task utilizing diffusion models. Our method, InpDiffusion, utilizes the denoising process enhanced by the integration of image semantic conditions to progressively refine predictions. During denoising, we employ edge conditions and introduce a novel edge supervision strategy to enhance the model's perception of edge details in inpainted objects. Balancing the diffusion model's stochastic sampling with edge supervision of tampered image regions mitigates the risk of incorrect predictions from overconfidence and prevents the loss of subtle boundaries that can result from overly stochastic processes. Furthermore, we propose an innovative Dual-stream Multi-scale Feature Extractor (DMFE) for extracting multi-scale features, enhancing feature representation by considering both semantic and edge conditions of the inpainted images. Extensive experiments across challenging datasets demonstrate that the InpDiffusion significantly outperforms existing state-of-the-art methods in IIL tasks, while also showcasing excellent generalization capabilities and robustness.
While most current image forgery localization (IFL) deep learning models focus primarily on the foreground of tampered images, they often neglect the essential complementary background semantic information. This oversight tends to create significant gaps in these models’ ability to thoroughly interpret and understand a tampered image, thereby limiting their effectiveness in extracting critical tampering traces. Given the above, this paper presents a novel contrastive learning and edge-reconstruction-driven complementary learning network (CECL-Net) for image forgery localization. CECL-Net enhances the understanding of tampered images by employing a complementary learning strategy that leverages foreground and background features, where a unique edge extractor (EE) generates precise edge artifacts, and edge-guided feature reconstruction (EGFR) utilizes the edge artifacts to reconstruct a fully complementary set of foreground and background features. To carry out the complementary learning process more efficiently, we also introduce a pixel-wise contrastive supervision (PCS) method that attracts consistent regions in features while repelling different regions. Moreover, we propose a dense fusion (DF) strategy that utilizes multi-scale and mutual attention mechanisms to extract more discriminative features and improve the representational power of CECL-Net. Experiments conducted on two benchmark datasets, one Artificial Intelligence (AI)-manipulated dataset and two real challenge datasets, indicate that our CECL-Net outperforms seven state-of-the-art models on three evaluation metrics.
As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a tendency towards overconfidence, leading to incorrect predictions; and difficulty in detecting subtle tampering boundaries in inpainted images. In response, we propose a new paradigm that treats IIL as a conditional mask generation task utilizing diffusion models. Our method, InpDiffusion, utilizes the denoising process enhanced by the integration of image semantic conditions to progressively refine predictions. During denoising, we employ edge conditions and introduce a novel edge supervision strategy to enhance the model's perception of edge details in inpainted objects. Balancing the diffusion model's stochastic sampling with edge supervision of tampered image regions mitigates the risk of incorrect predictions from overconfidence and prevents the loss of subtle boundaries that can result from overly stochastic processes. Furthermore, we propose an innovative Dual-stream Multi-scale Feature Extractor (DMFE) for extracting multi-scale features, enhancing feature representation by considering both semantic and edge conditions of the inpainted images. Extensive experiments across challenging datasets demonstrate that the InpDiffusion significantly outperforms existing state-of-the-art methods in IIL tasks, while also showcasing excellent generalization capabilities and robustness.
2 September 2025 in IEEE Transactions on Multimedia
To counter the security threats posed by the realism of image inpainting generated through diffusion models and GANs, in this paper, we propose a texture enhancement and progressive refinement network (TEPR-Net) for image inpainting localization (IIL). The IIL task is divided into two phases: coarse and fine locating. In the coarse locating phase, we utilize an anomaly texture encoder to capture tampering traces in textures, employ a texture–context feature interaction strategy to effectively integrate texture features with contextual features, and utilize a pixel-level contrastive learning strategy to enhance feature clustering and model generalization. In the fine locating phase, we first enhance the receptive field features in the frequency domain by transforming the features and separately enhancing the low- and high-frequency components. Then, we utilize the coarse localization result to augment the model's sensitivity to tampered regions. Additionally, we introduce a progressive edge distribution guidance and reconstruction strategy that progressively refines the edges of the tampered regions at each level, ultimately generating refined localization results. To support the research and evaluation of the IIL task, we create the Inpaint32K dataset, which is characterized by its large scale, diversity, comprehensiveness, high quality, and authenticity. Finally, extensive experiments demonstrate that TEPR-Net has significant advantages in terms of localization performance, generalizability, extensibility, and robustness.