Go to DBLP homepageM: Manipulation Mask Manufacturer for Arbitrary-Scale Super-Resolution Mask
Abstract: In the field of image manipulation localization (IML), the small quantity and poor quality of existing datasets have always been major issues. A dataset containing various types of manipulations will greatly help improve the accuracy of IML models. Images found on public forums, such as those in online image modification communities, are often manipulated using various techniques. Creating a dataset from these images can significantly enhance the diversity of manipulation types in our data. However, due to resolution and clarity issues, images obtained from the internet often contain noises, making it difficult to obtain clean masks by simply subtracting the manipulated image from the original. These noises are difficult to remove, rendering the masks unusable for IML models. Inspired by the field of change detection, we treat the original and manipulated images as changes over time for the same image and view the data generation task as a change detection task. Due to clarity issues between images, conventional change detection models perform poorly. Therefore, we introduced a super-resolution module and proposed the Manipulation Mask Manufacturer (MMM) framework, which enhances the resolution of both original and tampered images to improve comparison. Simultaneously, the framework converts the original and tampered images into feature embeddings and concatenates them, effectively modeling the context. Additionally, we used our MMM framework to create the Manipulation Mask Manufacturer Dataset (MMMD), which covers a wide range of manipulation techniques. We aim to contribute to the fields of image forensics and manipulation detection by providing more realistic manipulation data through MMM and MMMD. Detailed information about MMMD and the download link can be found at: https://github.com/ndyysheep/MMMD.
External IDs:dblp:conf/cvm/YangMZDSTLZ25
Loading