任意尺度超分辨率图像篡改掩膜生成方法

doi:10.19678/j.issn.1000-3428.0252288

摘要/Abstract

摘要：

在图像篡改定位(IML)领域, 现有数据集数量少、质量差, 难以支撑模型的泛化与鲁棒性。为此, 提出篡改掩膜生成(MMM)框架, 引入超分辨率模块以缓解原始图像与篡改图像清晰度差异带来的噪声问题, 并通过特征嵌入拼接与上下文建模生成高质量掩膜。基于MMM框架, 构建包含11 069对原始图像、篡改图像及掩膜的篡改掩膜生成数据集(MMMD), 其中涵盖复制移动、拼接、深度伪造(Deepfake)、图像修复和风格迁移等多种篡改方式。在CASIAv2、NIST16和IMD2020数据集上的实验结果表明, MMM框架取得了较好性能, 并在多种模型中展现出优良的泛化能力。进一步地, 使用MMMD预训练的MVSS-Net和IML-ViT在多个数据集上的F1值显著高于在传统数据集上预训练的模型, 凸显了MMMD在推动图像取证与篡改检测研究中的价值。

关键词: 图像篡改定位, 视觉媒体数据集, 数据集生成, 任意尺度, 超分辨率

Abstract:

In the field of Image Manipulation Localization (IML), the limited quantity and poor quality of existing datasets hinder model generalization and robustness. To address this, a Manipulation Mask Manufacturer (MMM) framework that integrates a super-resolution module to mitigate clarity discrepancies between the original and tampered images is proposed. The framework generates high-quality masks by embedding and concatenating features for effective context modeling. Based on the MMM framework, a Manipulation Mask Manufacturer Dataset (MMMD) is constructed, which contains 11 069 triplets of original images, manipulated images, and corresponding masks. MMMD encompasses diverse manipulation types, including copy-move, splicing, Deepfake, image inpainting, and style transfer. Experimental results demonstrate that MMM achieves strong performance on the CASIAv2, NIST16, and IMD2020 datasets, with F1 values of up to 0.96 and an Intersection over Union (IoU) of 0.90 on CASIAv2. Furthermore, models pretrained on MMMD, such as MVSS-Net and IML-ViT, consistently outperform those pretrained on conventional datasets across multiple benchmarks, highlighting the potential of the dataset to advance research in image forensics and manipulation detection.

Key words: Image Manipulation Localization (IML), dataset of visual media, dataset generation, arbitrary-scale, super-resolution

徐雄, 杨欣宇, 朱学康, 杜博, 粟磊, 童炳魁, 雷泽宇, 周吉喆. 任意尺度超分辨率图像篡改掩膜生成方法[J]. 计算机工程, 2025, 51(12): 277-284.

XU Xiong, YANG Xinyu, ZHU Xuekang, DU Bo, SU Lei, TONG Bingkui, LEI Zeyu, ZHOU Jizhe. Manipulation Mask Manufacturer for Arbitrary-Scale Super-Resolution Images[J]. Computer Engineering, 2025, 51(12): 277-284.

https://www.ecice06.com/CN/Y2025/V51/I12/277

图/表 9

图1 MMM框架

Fig.1 MMM framework

图2 CSLAB和LFEB的框架

Fig.2 The framework of CSLAB and LFEB

图3 MMM框架生成的结果图像

Fig.3 MMM framework-generated result images

图4 在MMMD上预训练的各种模型在不同数据集上的F1值可视化图

Fig.4 F1 values visualization chart of various models pre-trained by MMMD on different datasets

图5 在CASIAv2上预训练的各模型在各个数据集上的F1值可视化图

Fig.5 F1 values visualization chart of various models pre-trained by CASIAv2 on different datasets

参考文献 52

1	骆伟祺, 黄继武, 丘国平. 鲁棒的区域复制图像篡改检测技术. 计算机学报, 2007, 30 (11): 1998- 2007.
	LUO W Q , HUANG J W , QIU G P . Robust detection of region-duplication forgery in digital image. Chinese Journal of Computers, 2007, 30 (11): 1998- 2007.
2	FAULKNER A , CHAVEZ C . Adobe Photoshop CC classroom in a book. [S. l.]: Adobe Press, 2013.
3	GIMP Development Team. GIMP: GNU image manipulation program[EB/OL]. [2024-11-01]. https://www.gimp.org/.
4	FITZPATRICK N. Media manipulation 2.0: the impact of social media on news, competition, and accuracy[J]. Athens Journal of Mass Media and Communications, 2018, 4(1): 45-62.
5	FARID H . Image forgery detection. IEEE Signal Processing Magazine, 2009, 26 (2): 16- 25. doi: 10.1109/MSP.2008.931079
6	WANG W, DONG J, TAN T N. A survey of passive image tampering detection[M]//HO A T S, SHI Y Q, KIM H J, et al. Digital watermarking. Berlin, Germany: Springer, 2009: 308-322.
7	SU L, MA X C, ZHU X K, et al. Can we get rid of handcrafted feaure extractors? Sparsevit: nonsemantics-centered, parameter-efficient image manipulation localization through spare-coding transformer[EB/OL]. [2024-11-01]. https://arxiv.org/pdf/2307.14863v2.
8	DANG-NGUYEN D T, PASQUINI C, CONOTTER V, et al. RAISE: a raw images dataset for digital image forensics[C]//Proceedings of the 6th ACM Multimedia Systems Conference. New York, USA: ACM, 2015: 219-224.
9	YANG X Y, ZHOU J Z. Manipulation mask generator: high-quality image manipulation mask generation method based on modified total variation noise reduction[C]//Proceedings of the IEEE 4th International Conference on Pattern Recognition and Machine Learning (PRML). Washington D. C., USA: IEEE Press, 2023: 218-223.
10	BOUDIER T , SHOTTON D M . Video on the Internet: an introduction to the digital encoding, compression, and transmission of moving image data. Journal of Structural Biology, 1999, 125 (2/3): 133- 155.
11	RENSINK R A . Change detection. Annual Review of Psychology, 2002, 53, 245- 277. doi: 10.1146/annurev.psych.53.100901.135125
12	LU D , MAUSEL P , BRONDÍZIO E , et al. Change detection techniques. International Journal of Remote Sensing, 2004, 25 (12): 2365- 2401. doi: 10.1080/0143116031000139863
13	TAN Y , ZHENG H T , ZHU Y H , et al. CrossNet++: cross-scale large-parallax warping for reference-based super-resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43 (12): 4291- 4305. doi: 10.1109/TPAMI.2020.2997007
14	LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE Press, 2015: 3431-3440.
15	SEJDINOVIC D , SRIPERUMBUDUR B , GRETTON A , et al. Equivalence of distance-based and RKHS-based statistics in hypothesis testing. The Annals of Statistics, 2013, 41 (5): 2263- 2291.
16	LONG M S, CAO Y, WANG J M, et al. Learning transferable features with deep adaptation networks[C]//Proceedings of International Conference on Machine Learning. [S. l. ]: PMLR, 2015: 97-105.
17	CHEN H W, XU Y S, HONG M F, et al. Cascaded local implicit transformer for arbitrary-scale super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 18257-18267.
18	NOVOZAMSKY A, MAHDIAN B, SAIC S. IMD2020: a large-scale annotated dataset tailored for detecting manipulated images[C]//Proceedings of the IEEE Winter Applications of Computer Vision Workshops (WACVW). Snowmass Village, USA: IEEE Press, 2020: 71-80.
19	GUAN H Y, KOZAK M, ROBERTSON E, et al. MFC datasets: large-scale benchmark datasets for media forensic challenge evaluation[C]//Proceedings of the IEEE Winter Applications of Computer Vision Workshops (WACVW). Waikoloa Village, USA: IEEE Press, 2019: 63-72.
20	DONG J, WANG W, TAN T N. CASIA image tampering detection evaluation database[C]//Proceedings of the IEEE China Summit and International Conference on Signal and Information Processing. Beijing, China: IEEE Press, 2013: 422-426.
21	AMERINI I , BALLAN L , CALDELLI R , et al. A SIFT-based forensic method for copy-move attack detection and transformation recovery. IEEE Transactions on Information Forensics and Security, 2011, 6 (3): 1099- 1110. doi: 10.1109/TIFS.2011.2129512
22	CHRISTLEIN V , RIESS C , JORDAN J , et al. An evaluation of popular copy-move forgery detection approaches. IEEE Transactions on Information Forensics and Security, 2012, 7 (6): 1841- 1854. doi: 10.1109/TIFS.2012.2218597
23	HSU Y F, CHANG S F. Detecting image splicing using geometry invariants and camera characteristics consistency[C]//Proceedings of the IEEE International Conference on Multimedia and Expo. Toronto, Canada: IEEE Press, 2006: 549-552.
24	PETROU M M P , PETROU C . Image processing: the fundamentals. [S. l.]: John Wiley & Sons, Inc, 2010.
25	MIRSKY Y , LEE W K . The creation and detection of deepfakes. ACM Computing Surveys, 2022, 54 (1): 1- 41.
26	ELHARROUSS O , ALMAADEED N , AL-MAADEED S , et al. Image inpainting: a review. Neural Processing Letters, 2020, 51 (2): 2007- 2028. doi: 10.1007/s11063-019-10163-0
27	WOLBERG G . Image morphing: a survey. The Visual Computer, 1998, 14 (8): 360- 372.
28	DEMOMENT G . Image reconstruction and restoration: overview of common estimation structures and problems. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1989, 37 (12): 2024- 2036. doi: 10.1109/29.45551
29	JING Y C , YANG Y Z , FENG Z L , et al. Neural style transfer: a review. IEEE Transactions on Visualization and Computer Graphics, 2020, 26 (11): 3365- 3385. doi: 10.1109/TVCG.2019.2921336
30	DONG C B , CHEN X R , HU R H , et al. MVSS-Net: multi-view multi-scale supervised networks for image manipulation detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (3): 3539- 3553. doi: 10.1109/TPAMI.2022.3180556
31	MA X C, DU B, LIU X G, et al. IML-ViT: Image manipulation localization by vision transformer[EB/OL]. [2024-11-01]. https://arxiv.org/pdf/2307.14863.
32	THAKUR R , ROHILLA R . Recent advances in digital image manipulation detection techniques: a brief review. Forensic Science International, 2020, 312, 110311. doi: 10.1016/j.forsciint.2020.110311
33	WEN B H, ZHU Y, SUBRAMANIAN R, et al. COVERAGE—a novel database for copy-move forgery detection[C]//Proceedings of the IEEE International Conference on Image Processing (ICIP). Phoenix, USA: IEEE Press, 2016: 161-165.
34	CHEN H , QI Z P , SHI Z W . Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60, 1- 14.
35	BANDARA W G C, PATEL V M. A transformer-based Siamese network for change detection[C]//Proceedings of the 2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur, Malaysia: IEEE Press, 2022: 207-210.
36	ZHU X K, MA X C, SU L, et al. Mesoscopic insights: orchestrating multi-scale & hybrid architecture for image manipulation localization[EB/OL]. [2024-11-01]. https://arxiv.org/pdf/2412.13753.
37	FANG S , LI K Y , SHAO J Y , et al. SNUNet-CD: a densely connected Siamese network for change detection of VHR images. IEEE Geoscience and Remote Sensing Letters, 2022, 19, 1- 5.
38	SHI J B , MALIK J . Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (8): 888- 905. doi: 10.1109/34.868688
39	ANDREADIS I, AMANATIADIS A. Digital image scaling[C]//Proceedings of the IEEE Instrumentationand Measurement Technology Conference. Ottawa, Canada: IEEE Press, 2005: 2028-2032.
40	GINSBERG R H . Image rotation. Applied Optics, 1994, 33 (34): 8105_1. doi: 10.1364/AO.33.8105_1
41	CRIMINISI A , PEREZ P , TOYAMA K . Region filling and object removal by exemplar-based image inpainting. IEEE Transactions on Image Processing, 2004, 13 (9): 1200- 1212. doi: 10.1109/TIP.2004.833105
42	GLASBEY C A , MARDIA K V . A review of image-warping methods. Journal of Applied Statistics, 1998, 25 (2): 155- 171. doi: 10.1080/02664769823151
43	MAHFOUDI G, TAJINI B, RETRAINT F, et al. DEFACTO: image and face manipulation dataset[C]//Proceedings of the 27th European Signal Processing Conference (EUSIPCO). A Coruna, Spain: IEEE Press, 2019: 1-5.
44	LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of ECCV 2014. Berlin, Germany: Springer, 2014: 740-755.
45	ZHUANG P Y , LI H D , TAN S Q , et al. Image tampering localization using a dense fully convolutional network. IEEE Transactions on Information Forensics and Security, 2021, 16, 2986- 2999. doi: 10.1109/TIFS.2021.3070444
46	MA X C, ZHU X K, SU L, et al. IMDL-BenCo: a comprehensive benchmark and codebase for image manipulation detection & localization[EB/OL]. [2024-11-01]. https://arxiv.org/pdf/2406.10580.
47	WU Y, ABDALMAGEED W, NATARAJAN P. ManTra-Net: manipulation tracing network for detection and localization of image forgeries with anomalous features[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE Press, 2019: 9535-9544.
48	KWON M J , NAM S H , YU I J , et al. Learning JPEG compression artifacts for image manipulation detection and localization. International Journal of Computer Vision, 2022, 130 (8): 1875- 1895. doi: 10.1007/s11263-022-01617-5
49	WANG J K, WU Z X, CHEN J J, et al. ObjectFormer for image manipulation detection and localization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, USA: IEEE Press, 2022: 2354-2363.
50	ZHOU J Z, MA X C, DU X, et al. Pre-training-free image manipulation localization through non-mutually exclusive contrastive learning[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France: IEEE Press, 2023: 22289-22299.
51	GUILLARO F, COZZOLINO D, SUD A, et al. TruFor: leveraging all-round clues for trustworthy image forgery detection and localization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 20606-20615.
52	LIU X H , LIU Y J , CHEN J , et al. PSCC-Net: progressive spatio-channel correlation network for image manipulation detection and localization. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32 (11): 7505- 7517. doi: 10.1109/TCSVT.2022.3189545

[1]	王震, 陈希爱, 杨超, 贾慧迪, 韩志, 唐延东. 基于空谱先验与高阶张量表示的超分辨率重建算法[J]. 计算机工程, 2025, 51(9): 220-230.
[2]	赵瑶谦, 滕奇志, 何小海, 税爱, 陈洪刚. 基于自注意力特征蒸馏的轻量级图像超分辨率重建[J]. 计算机工程, 2025, 51(5): 257-265.
[3]	张天鹏, 韩晶, 吕学强. 基于多任务学习的超分辨率辅助小目标检测[J]. 计算机工程, 2024, 50(9): 304-312.
[4]	李大海, 吕春桂, 王振东. 基于双分支序列残差注意力的场景文本图像超分辨率重建[J]. 计算机工程, 2024, 50(9): 286-295.
[5]	王志浩, 钱沄涛. 基于Swin Transformer的双流遥感图像时空融合超分辨率重建[J]. 计算机工程, 2024, 50(9): 33-45.
[6]	杨郅树, 梁佳楠, 曹永军, 钟震宇, 何永伦. 基于局部分离与多尺度融合的图像超分辨率重建[J]. 计算机工程, 2024, 50(7): 314-323.
[7]	李志鹏, 陈丹阳, 钟诚. 一种改进的超分辨率轻量化特征融合方法[J]. 计算机工程, 2024, 50(11): 258-265.
[8]	杨雨迪, 葛海波, 辛世澳, 薛紫涵, 袁昊. 融合超分辨率和特征增强的轻量化遥感图像小目标检测[J]. 计算机工程, 2024, 50(11): 284-296.
[9]	范文卓, 吴涛, 许俊平, 李庆庆, 张建林, 李美惠, 魏宇星. 基于多分辨率特征融合的任意尺度图像超分辨率重建[J]. 计算机工程, 2023, 49(9): 217-225.
[10]	王同官, 赖惠成, 蔡玉玺, 高古学, 汪烈军. 基于注意力残差网络的人脸超分辨率重建[J]. 计算机工程, 2023, 49(6): 234-241.
[11]	丁子轩, 俞雷, 张娟, 李想, 王新宇. 基于深度残差自适应注意力网络的图像超分辨率重建[J]. 计算机工程, 2023, 49(5): 231-238.
[12]	李培育, 张雅丽. 基于改进SRGAN模型的人脸图像超分辨率重建[J]. 计算机工程, 2023, 49(4): 199-205.
[13]	黎浩民, 李光平. 基于稀疏神经网络的图像超分辨率重建算法[J]. 计算机工程, 2022, 48(7): 247-253.
[14]	柳聪, 屈丹, 司念文, 魏紫薇. 基于深度可分离卷积的轻量级图像超分辨率重建[J]. 计算机工程, 2022, 48(6): 228-234.
[15]	楼鑫杰, 李小薪, 刘志勇. 基于反馈机制的图像超分辨率重建算法[J]. 计算机工程, 2022, 48(2): 261-267.

选择文件类型/文献管理软件名称

选择包含的内容