# Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

arXiv: https://arxiv.org/abs/2404.17310 · HTML: https://mlsanity.com/paper/2404.17310/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 43 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 7 of 7)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Two-Stage Copy-Move Forgery Detection with Self Deep Matching and Proposal SuperGlue](https://mlsanity.com/paper/2012.08697/) (2020)
- [Copy Move Source-Target Disambiguation through Multi-Branch CNNs](https://mlsanity.com/paper/1912.12640/) (2019)
- [Shrinking the Semantic Gap: Spatial Pooling of Local Moment Invariants for Copy-Move Forgery Detection](https://mlsanity.com/paper/2207.09135/) (2022)
- [Image Copy-Move Forgery Detection via Deep Cross-Scale PatchMatch](https://mlsanity.com/paper/2308.04188/) (2023)

## Built on by (most cited first, 2 of 2)

- [Toward Generalizable Forgery Detection and Reasoning](https://mlsanity.com/paper/2503.21210/) (2025)
- [ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization](https://mlsanity.com/paper/2410.10238/) (2024)

## Abstract (arXiv)

Recent advances in deep learning algorithms have shown impressive progress in image copy-move forgery detection (CMFD). However, these algorithms lack generalizability in practical scenarios where the copied regions are not present in the training images, or the cloned regions are part of the background. Additionally, these algorithms utilize convolution operations to distinguish source and target regions, leading to unsatisfactory results when the target regions blend well with the background. To address these limitations, this study proposes a novel end-to-end CMFD framework that integrates the strengths of conventional and deep learning methods. Specifically, the study develops a deep cross-scale PatchMatch (PM) method that is customized for CMFD to locate copy-move regions. Unlike existing deep models, our approach utilizes features extracted from high-resolution scales to seek explicit and reliable point-to-point matching between source and target regions. Furthermore, we propose a novel pairwise rank learning framework to separate source and target regions. By leveraging the strong prior of point-to-point matches, the framework can identify subtle differences and effectively discriminate between source and target regions, even when the target regions blend well with the background. Our framework is fully differentiable and can be trained end-to-end. Comprehensive experimental results highlight the remarkable generalizability of our scheme across various copy-move scenarios, significantly outperforming existing methods.