# Image Copy-Move Forgery Detection via Deep Cross-Scale PatchMatch

arXiv: https://arxiv.org/abs/2308.04188 · HTML: https://mlsanity.com/paper/2308.04188/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 15 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 2 of 2)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)

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

- [Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning](https://mlsanity.com/paper/2404.17310/) (2024)
- [An Effective Image Copy-Move Forgery Detection Using Entropy Information](https://mlsanity.com/paper/2312.11793/) (2023)

## Abstract (arXiv)

The recently developed deep algorithms achieve promising progress in the field of image copy-move forgery detection (CMFD). However, they have limited generalizability in some practical scenarios, where the copy-move objects may not appear in the training images or cloned regions are from the background. To address the above issues, in this work, we propose a novel end-to-end CMFD framework by integrating merits from both conventional and deep methods. Specifically, we design a deep cross-scale patchmatch method tailored for CMFD to localize copy-move regions. In contrast to existing deep models, our scheme aims to seek explicit and reliable point-to-point matching between source and target regions using features extracted from high-resolution scales. Further, we develop a manipulation region location branch for source/target separation. The proposed CMFD framework is completely differentiable and can be trained in an end-to-end manner. Extensive experimental results demonstrate the high generalizability of our method to different copy-move contents, and the proposed scheme achieves significantly better performance than existing approaches.