Scholarlink

In this paper, we propose a technique to detect and localize inpainting created by diffusion-based machine learning models. We begin by compiling a dataset of inpainted images, which we then use to train a convolutional neural network (CNN) for this task. Our method achieves high precision, recall, F1-score, and Intersection over Union (IoU) in detecting and localizing inpainting. It is versatile and can be applied to various real-life scenarios.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

InpaintLocalizer: Detection and Localization of Inpainting Generated by Diffusion-Based Machine Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Giorgio De Magistris,
  • Marco Lo Pinto,
  • Patryk Najgebauer,
  • Rafał Scherer,
  • Christian Napoli

摘要

In this paper, we propose a technique to detect and localize inpainting created by diffusion-based machine learning models. We begin by compiling a dataset of inpainted images, which we then use to train a convolutional neural network (CNN) for this task. Our method achieves high precision, recall, F1-score, and Intersection over Union (IoU) in detecting and localizing inpainting. It is versatile and can be applied to various real-life scenarios.