COCO-Inpaint: A Benchmark for Image Inpainting Detection and Manipulation Localization
This addresses the problem of multimedia authenticity and cybersecurity for researchers and practitioners by providing a specialized benchmark, though it is incremental as it builds on existing IMDL frameworks.
The authors tackled the lack of dedicated benchmarks for inpainting-based image manipulations by introducing COCO-Inpaint, a comprehensive dataset with 258,266 inpainted images generated using six state-of-the-art models and four mask strategies, enabling rigorous evaluation of detection methods.
Recent advancements in image manipulation have achieved unprecedented progress in generating photorealistic content, but also simultaneously eliminating barriers to arbitrary manipulation and editing, raising concerns about multimedia authenticity and cybersecurity. However, existing Image Manipulation Detection and Localization (IMDL) methodologies predominantly focus on splicing or copy-move forgeries, lacking dedicated benchmarks for inpainting-based manipulations. To bridge this gap, we present COCOInpaint, a comprehensive benchmark specifically designed for inpainting detection, with three key contributions: 1) High-quality inpainting samples generated by six state-of-the-art inpainting models, 2) Diverse generation scenarios enabled by four mask generation strategies with optional text guidance, and 3) Large-scale coverage with 258,266 inpainted images with rich semantic diversity. Our benchmark is constructed to emphasize intrinsic inconsistencies between inpainted and authentic regions, rather than superficial semantic artifacts such as object shapes. We establish a rigorous evaluation protocol using three standard metrics to assess existing IMDL approaches. The dataset will be made publicly available to facilitate future research in this area.