浏览全部资源
扫码关注微信
收稿日期：2024-11-15，
修回日期：2025-04-03，
录用日期：2025-04-09，
网络出版日期：2025-04-09，
移动端阅览
目的
2
图像和视频合成技术在媒体后期处理领域广泛应用，随着技术门槛的降低，大量合成素材被发布并迅速传播。然而，部分合成内容可能含有误导性信息，威胁视听内容的真实性和安全性。传统合成检测方法主要依赖合成痕迹或画面异常检测，但随着合成技术的不断进步，现有方法在检测精度和适应性方面仍存在优化空间，需要改进以应对日益复杂的合成内容检测需求。
方法
2
本文提出一种融合物理与深度学习的合成图像检测方法，创新性地结合光照和阴影一致性分析。通过特征提取与融合网络，实现光照图与光照强度的一致性分析，判断物体采集环境；利用交比估计检测光照方向一致性，有效提升了检测精度和适应性。同时构建了具有物理属性的数据集，为合成图像检测提供数据支持。
结果
2
在NIST 16、Coverage和CASIA数据集上的实验表明，本文方法在AUC指标上分别达到94.2%、93.6%和90.3%，F1分数分别达到80.2%、79.3%和58.1%，优于对比方法。在噪声攻击实验中，本文方法对尺寸变化、高斯模糊、高斯噪声和JPEG压缩表现出更强的适应性，平均AUC为84.03%。此外，本文提出的数据集在训练过程中表现出高可用性，使用该数据集训练的模型AUC平均提升18.1%。
结论
2
本文提出的方法在准确性和鲁棒性方面均优于对比方法，构建的数据集能够有效支持合成图像检测模型的训练、验证和测试，为该领域的研究提供了重要参考。
Synthesis and forgery of media content such as images and videos have become common methods in media post-production. As the technical barriers gradually decrease， the internet is disseminated with a large amount of synthetic materials， posing significant challenges to the integrity and security of digital media， affecting the authenticity and safety of audiovisual content.In the realm of synthetic media detection， research has surged to the forefront in recent years. Most commonly used detection methods focus on physical attributes or directly utilize deep neural networks for detection. Image forgery detection methods based on physical attributes can be broadly divided into those that utilize physical features and those that employ deep neural networks. Methods relying on physical features identify visual inconsistencies in images， leveraging the fact that synthetic images are often composed of multiple stitched images， which can result in irregularities in lighting， shadows， depth of field， and object distance. Inconsistency detection involves examining inherent physical properties such as lighting and shadows to assess their coherence. Lighting detection methods primarily analyze factors like light source position， chromatic deviation， object reflectivity， light source color， and local light sources. Shadow detection methods focus on properties such as planar homology， shadow constraints， vanishing point positions for light and shadow， and consistency in geometric relationships. However， due to the diverse and complex environments in which images are acquired， the high precision required by these physical detection methods makes it challenging to rely solely on a single approach for forgery detection in real-world scenarios.In image forgery detection methods based on deep neural networks， some approaches use Long Short-Term Memory （LSTM）， dual stream parallel network， pyramid architectures， Transformers etc.， to conduct synthesis detection by identifying anomalies in local regions between image blocks while locating synthesized areas. While these methods have demonstrated certain levels of success in experimental settings， the relentless advancement in synthesis technology has resulted in synthetic images that are increasingly indistinguishable from authentic ones. As a result， detection methods relying solely on visual anomalies or signs of synthesis can no longer meet the growing demands for accuracy in detection.We present a novel approach LSFNet to image forgery detection based on the consistency of lighting and shadows. It combines highly sensitive physical attribute detection with robust deep neural network techniques， improving the ability to identify even the most meticulously crafted synthetic images. LSFNet comprises key modules， including illumination maps， object and shadow estimation， illumination analysis， and homogeneity analysis. Its goal is to integrate physical detection methods like illumination and shadow with deep neural network techniques for effective detection of well-crafted synthetic images. The method begins by creating an illumination map that labels the object and shadow areas， resulting in a boundary illumination map formed by overlapping the illumination map with the object area. This paper employs a feature extraction network to derive features from both the boundary illumination map and the original image， establishing a feature fusion network for consistency analysis of the illumination map and light intensity to determine the shooting environment of objects within the image. It estimates distances for objects and shadows using cross-ratio for homogeneous vertex estimation to ensure consistent detection of lighting direction in images. Finally， this paper utilizes result fusion methods to comprehensively evaluate both lighting analysis results and homogeneity analysis results to predict outcomes for synthetic images. Additionally， recognizing that existing datasets for synthetic image detection often lack detailed information about physical attributes， we introduce a new dataset designed to assist in detecting synthetic images by incorporating essential characteristics such as lighting conditions and object distances crucial for accurately identifying forgery in today’s complex digital media landscape.The contributions of this paper are summarized as follows：（1） We propose a versatile image forgery detection framework for high-fidelity synthetic images， called the Lighting and Shadow Fusion Network （LSFNet）. This framework integrates deep neural networks with physical detection methods， combining boundary lighting map detection and physical attribute consistency analysis. Experimental results show that our method outperforms mainstream techniques in accuracy and demonstrates robustness， making it suitable for various synthetic image detection tasks；（2） We present a shadow extraction and consistency analysis method tailored for image forgery detection. Utilizing Mask R-CNN as the backbone network for shadow prediction， this approach models the relationship between shadow regions and real object areas. By assessing consistency through intersection over union （IoU）， it significantly enhances the accuracy of image forgery detection；（3） We introduce a synthetic image detection dataset featuring physical attributes such as light source position， color temperature， camera position， object distance， depth of field， and complex backgrounds. Named the Synthetic Image Physical Properties Detection （SIPD） dataset， it comprises 22，203 images-15，012 collected images and 7，191 synthetically generated ones—all meticulously crafted by professionals to ensure high realism. The dataset maintains a training-validation-testing split of 7：2：1 and includes various synthesis methods like stitching， copy-pasting， and deletion to effectively support training testing and optimization upgrades for image forgery detection models.
Atak I G ， and Yasar A . Image forgery detection by combining visual transformer with variational autoencoder network . Applied Soft Computing ， 2024 ， 165 ： 112068 ［ DOI： 10.1016/j.asoc.2024.112068 http://dx.doi.org/10.1016/j.asoc.2024.112068 ］
Bai R . Image manipulation detection and localization using multi-scale contrastive learning . Applied Soft Computing ， 2024 ， 163 ： 111914 ［ DOI： 10.1016/j.asoc.2024.111914 http://dx.doi.org/10.1016/j.asoc.2024.111914 ］
Bappy M J H ， Roy-Chowdhury A K ， Bunk J ， Nataraj L ， and Manjunath B S . Exploiting spatial structure for localizing manipulated image regions . In： 2017 IEEE International Conference on Computer Vision （ICCV） . IEEE Computer Society ； 2017 ［DOI： 10.1109/ICCV.2017.532］
Bappy M J H ， Simons C ， Nataraj L ， Manjunath B S ， and Roy-Chowdhury A K . Hybrid LSTM and encoder-decoder architecture for detection of image forgeries . IEEE Transactions on Image Processing ， 2019 ， 28 （ 6 ）： 1706 - 1719 ［ DOI： 10.1109/TIP.2019.2895466 http://dx.doi.org/10.1109/TIP.2019.2895466 ］
Bunk J ， Bappy J H ， Mohammed T M ， et al . Detection and localization of image forgeries using resampling features and deep learning . In： 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops （CVPRW） . IEEE ； 2017 ［DOI： 10.1109/CVPRW.2017.235］
Chen J ， Yang G ， Ding X ， Guo Z ， and Wang S . Robust detection of dehazed image via dual-stream CNNs with adaptive feature fusion . Computer Vision and Image Understanding ， 2022 ， 221 ： 103357 ［ DOI： 10.1016/j.cviu.2022.103357 http://dx.doi.org/10.1016/j.cviu.2022.103357 ］
Chen X ， Yan B ， Zhu J ， Wang D ， Yang X ， and Lu H . Transformer tracking . In： Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2021 ： 8126 - 8135 ［ DOI： 10.1109/CVPR46437.2021.00803 http://dx.doi.org/10.1109/CVPR46437.2021.00803 ］
Chen Z ， Wan L ， Zhu L ， Shen J ， Fu H ， Liu W ， and Qin J . Triple-cooperative video shadow detection . In： Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2021 ： 2715 - 2724 ［ DOI： 10.48550/arXiv.2103.06533 http://dx.doi.org/10.48550/arXiv.2103.06533 ］
CISION . Axalta extends automotive color leadership with the 69th Global Automotive Color Popularity Report . 2021 . ［EB/OL］. （ 2021-12-21 ）. https://www.prnewswire.com/news-releases/axalta-extends-automotive-color-lead https://www.prnewswire.com/news-releases/axalta-extends-automotive-color-lead .
Crowson K ， Biderman S ， Kornis D ， Stander D ， Hallahan E ， Castricato L ， and Raff E . VQGAN-CLIP： Open domain image generation and editing with natural language guidance . 2022 ［ DOI： 10.48550/arXiv.2204.08583 http://dx.doi.org/10.48550/arXiv.2204.08583 ］
Ding B ， Long C ， Zhang L ， and Xiao C . ARGAN： Attentive recurrent generative adversarial network for shadow detection and removal . In： 2019 IEEE/CVF International Conference on Computer Vision （ICCV） . IEEE ； 2020 ： 6721 - 6730 ［ DOI： 10.1109/ICCV.2019.01031 http://dx.doi.org/10.1109/ICCV.2019.01031 ］
Dong J ， Wang W ， and Tan T . CASIA image tampering detection evaluation database . In： 2013 IEEE China Summit & International Conference on Signal and Information Processing （ChinaSIP） . IEEE ； 2013 ［DOI： 10.1109/ChinaSIP.2013.6625374］
Gholap S ， and Bora P K . Illuminant colour based image forensics . In： 2008 IEEE Region 10 Conference （TENCON） . IEEE ； 2008 ［DOI： 10.1109/TENCON.2008.4766772］
Guo R ， Dai Q ， and Hoiem D . Single-image shadow detection and removal using paired regions . In： 2011 IEEE Conference on Computer Vision and Pattern Recognition （CVPR） . IEEE ； 2011 ： 2033 - 2040 ［ DOI： 10.1109/CVPR.2011.5995725 http://dx.doi.org/10.1109/CVPR.2011.5995725 ］
Guo X ， Liu X ， Masi I ， and Liu X . Language-guided hierarchical fine-grained image forgery detection and localization . International Journal of Computer Vision ， 2024 ［ DOI： 10.1007/s11263-024-02255-9 http://dx.doi.org/10.1007/s11263-024-02255-9 ］
Hadwiger B C ， and Riess C . Deep metric color embeddings for splicing localization in severely degraded images . IEEE Transactions on Information Forensics and Security ， 2022 ， 17 ： 2614 - 2627 ［ DOI： 10.1109/TIFS.2022.3189527 http://dx.doi.org/10.1109/TIFS.2022.3189527 ］
Han R ， Wang X ， Bai N ， Wang Y ， Hou J ， and Xue J . HDF-Net： Capturing homogeny difference features to localize the tampered image . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2024 ［ DOI： 10.1109/TPAMI.2024.3432551 http://dx.doi.org/10.1109/TPAMI.2024.3432551 ］
Hao J ， Zhang Z ， Yang S ， Xie D ， and Pu S . TransForensics： Image forgery localization with dense self-attention . 2021 ［ DOI： 10.48550/arXiv.2108.03871 http://dx.doi.org/10.48550/arXiv.2108.03871 ］
Hao Q ， Ren R ， Niu S ， Xie D ， and Pu S . UGEE-Net： Uncertainty-guided and edge-enhanced network for image splicing localization . Neural Networks ， 2024 ， 178 ： 106430 ［ DOI： 10.1016/j.neunet.2024.106430 http://dx.doi.org/10.1016/j.neunet.2024.106430 ］
He K ， Gkioxari G ， Dollár P ， and Girshick R . Mask R-CNN . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2020 ， 42 （ 2 ）： 386 - 397 ［ DOI： 10.1109/TPAMI.2018.2844175 http://dx.doi.org/10.1109/TPAMI.2018.2844175 ］
He K ， Zhang X ， Ren S ， and Sun J . Deep residual learning for image recognition . In： Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR） . 2016 ： 770 - 778 ［ DOI： 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ］
Hu X ， Wang T ， Fu C W ， Jiang Y ， Wang Q ， and Heng P A . Revisiting shadow detection： A new benchmark dataset for complex world . IEEE Transactions on Image Processing ， 2021 ， 30 ： 8145 - 8156 ［ DOI： 10.1109/TIP.2021.3049331 http://dx.doi.org/10.1109/TIP.2021.3049331 ］
Hu X ， Zhang Z ， Jiang Z ， Chaudhuri S ， and Yang Z . SPAN： Spatial pyramid attention network for image manipulation localization . In ： Computer Vision-ECCV 2020 . Springer； 2020 ： 312 - 328 ［ DOI： 10.1007/978-3-030-58589-1_19 http://dx.doi.org/10.1007/978-3-030-58589-1_19 ］
Huang X ， Hua G ， Tumblin J ， and Williams L . What characterizes a shadow boundary under the sun and sky？ In： 2011 International Conference on Computer Vision . IEEE ； 2011 ： 898 - 905 ［ DOI： 10.1109/ICCV.2011.6126331 http://dx.doi.org/10.1109/ICCV.2011.6126331 ］
Johnson M K ， and Farid H . Exposing digital forgeries in complex lighting environments . IEEE Transactions on Information Forensics and Security ， 2007 ， 2 （ 3 ）： 450 - 461 ［ DOI： 10.1109/TIFS.2007.903848 http://dx.doi.org/10.1109/TIFS.2007.903848 ］
Johnson M K ， and Farid H . Exposing digital forgeries through chromatic aberration . In： Proceedings of the 8th Workshop on Multimedia and Security . ACM ； 2006 ： 48 - 55 ［ DOI： 10.1145/1161366.1161376 http://dx.doi.org/10.1145/1161366.1161376 ］
Kee E ， O'Brien J F ， and Farid H . Exposing photo manipulation with inconsistent shadows . ACM Transactions on Graphics ， 2013 ， 32 （ 3 ）： 1 - 12 ［ DOI： 10.1145/2487228.2487236 http://dx.doi.org/10.1145/2487228.2487236 ］
Lahiri A ， Jain A K ， Agrawal S ， Mitra P ， and Biswas P K . Prior guided GAN based semantic inpainting . In： 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . IEEE ； 2020 ： 13693 - 13702 ［ DOI： 10.1109/CVPR42600.2020.01371 http://dx.doi.org/10.1109/CVPR42600.2020.01371 ］
Lalonde J-F ， Efros A A ， and Narasimhan S G . Detecting ground shadows in outdoor consumer photographs . In ： European Conference on Computer Vision 2010 . Springer； 2010 ： 322 - 335 ［ DOI： 10.1007/978-3-642-15552-9_24 http://dx.doi.org/10.1007/978-3-642-15552-9_24 ］
Le H ， Vicente T F Y ， Nguyen V ， Hoai M ， and Samaras D . A+D Net： Training a shadow detector with adversarial shadow attenuation . In ： European Conference on Computer Vision 2018 . Springer； 2018 ： 680 - 696 ［ DOI： 10.1007/978-3-030-01216-8_41 http://dx.doi.org/10.1007/978-3-030-01216-8_41 ］
Lee C ， Liu Z ， Wu L ， and Luo P . MaskGAN： Towards diverse and interactive facial image manipulation . In： 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . IEEE ； 2020 ： 5548 - 5557 ［ DOI： 10.1109/CVPR42600.2020.00559 http://dx.doi.org/10.1109/CVPR42600.2020.00559 ］
Lin T-Y ， Dollár P ， Girshick R ， Hariharan B ， and Belongie S . Feature pyramid networks for object detection . In： Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR） . 2017 ： 2117 - 2125 ［ DOI： 10.1109/CVPR.2017.106 http://dx.doi.org/10.1109/CVPR.2017.106 ］
Liu W ， Zhang H ， Lin X ， Zhang Q ， Li Q ， Liu X ， and Cao Y . Attentive and contrastive image manipulation localization with boundary guidance . IEEE Transactions on Information Forensics and Security ， 2024 ［ DOI： 10.1109/TIFS.2024.3424987 http://dx.doi.org/10.1109/TIFS.2024.3424987 ］
Liu X ， Lin Z ， Zhang J ， Zhao H ， Tran Q ， Wang X ， and Li H . Open-edit： Open-domain image manipulation with open-vocabulary instructions . In ： Computer Vision-ECCV 2020 . Springer； 2020 ： 89 - 106 ［ DOI： 10.1007/978-3-030-58621-8_6 http://dx.doi.org/10.1007/978-3-030-58621-8_6 ］
Liu X ， Liu Y ， and Chen J . 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 ）： 7523 - 7535 ［ DOI： 10.1109/TCSVT.2022.3189545 http://dx.doi.org/10.1109/TCSVT.2022.3189545 ］
Kumar D S ， Gladiss N R ， Cristin R ， and Sekar A . Improved Segmentation Techniques for Image Manipulation with Shadow-Based Digital Forgery Using Vanishing Point Computation . International Journal of Scientific & Technology Research ， 2019 ， 8 （ 12 ）： 504 - 507 .
Nasiri M ， and Behrad A . Using Expectation-Maximization for Exposing Image Forgeries by Revealing Inconsistencies in Shadow Geometry . Journal of Visual Communication and Image Representation ， 2019 ， 58 ： 323 - 333 ［ DOI： 10.1016/j.jvcir.2018.12.007 http://dx.doi.org/10.1016/j.jvcir.2018.12.007 ］
Ng T T ， and Chang S F . A Data Set of Authentic and Spliced Image Blocks . Columbia University Technical Report ， 2004 .
Nillius P ， and Eklundh J O . Automatic Estimation of the Projected Light Source Direction . In： 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition （CVPR） . IEEE ； 2001 ： 1076 - 1083 ［ DOI： 10.1109/CVPR.2001.990650 http://dx.doi.org/10.1109/CVPR.2001.990650 ］
Nilroy F F ， Bhaumik K K ， and Woo S S . CFL-Net： Image Forgery Localization Using Contrastive Learning . In： 2023 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . 2023 ： 4631 - 4640 ［ DOI： 10.1109/WACV56688.2023.00462 http://dx.doi.org/10.1109/WACV56688.2023.00462 ］
NIST . NIST Nimble 2016 datasets . 2016. ［Online］. Available： https：//www.nist.gov/itl/iad/mig/nimble-challenge-2017-evaluation/ https://www.nist.gov/itl/iad/mig/nimble-challenge-2017-evaluation/
Novozamsky A ， Mahdian B ， and Saic S . Extended IMD2020： A large-scale annotated dataset tailored for detecting manipulated images . IET Biometrics ， 2021 ， 10 （ 3 ）： 312 - 325 ［ DOI： 10.1049/bme2.12025 http://dx.doi.org/10.1049/bme2.12025 ］
Palmer C J ， Goddard E ， and Clifford C W G . Face detection from patterns of shading and shadows： The role of overhead illumination in generating the familiar appearance of the human face . Cognition ， 2022 ， 225 ： 105172 ［ DOI： 10.1016/j.cognition.2022.105172 http://dx.doi.org/10.1016/j.cognition.2022.105172 ］
Pan W ， Ma W ， Zhao S ， Gu L ， Shi G ， Xia Z ， and Wang M . Image manipulation detection with cascade hierarchical graph representation . IEEE Transactions on Circuits and Systems for Video Technology ， 2024 ［ DOI： 10.1109/TCSVT.2024.3390127 http://dx.doi.org/10.1109/TCSVT.2024.3390127 ］
Park J S ， Cho D ， Ahn W ， and Lee H K . Double JPEG detection in mixed JPEG quality factors using deep convolutional neural network . In ： European Conference on Computer Vision （ECCV） 2018 . Springer； 2018 ： 636 - 653 ［ DOI： 10.1007/978-3-030-01228-1_39 http://dx.doi.org/10.1007/978-3-030-01228-1_39 ］
Pomari T ， Ruppert G ， Rezende E ， Rocha A ， and Carvalho T . Image splicing detection through illumination inconsistencies and deep learning . In： 2018 IEEE International Conference on Image Processing （ICIP） . 2018 ： 3788 - 3792 ［ DOI： 10.1109/ICIP.2018.8451227 http://dx.doi.org/10.1109/ICIP.2018.8451227 ］
Ren S ， He K ， Girshick R ， and Sun J . Faster R-CNN： Towards real-time object detection with region proposal networks . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2017 ， 39 （ 6 ）： 1137 - 1149 ［ DOI： 10.1109/TPAMI.2016.2577031 http://dx.doi.org/10.1109/TPAMI.2016.2577031 ］
Riess C ， and Angelopoulou E . Scene illumination as an indicator of image manipulation . In ： Computer Vision–ECCV 2010 . Springer； 2010 ： 66 - 79 ［ DOI： 10.1007/978-3-642-16435-4_6 http://dx.doi.org/10.1007/978-3-642-16435-4_6 ］
Salloub R ， Ren Y ， and Jay Kuo C-C . Image splicing localization using a multi-task fully convolutional network （MFCN） . Journal of Visual Communication and Image Representation ， 2018 ， 51 ： 201 - 209 ［ DOI： 10.1016/j.jvcir.2018.01.010 http://dx.doi.org/10.1016/j.jvcir.2018.01.010 ］
Sekhar C P ， and Shankar T . Splicing forgery localisation using colour illumination inconsistencies . International Journal of Electronic Security and Digital Forensics ， 2021 ， 13 （ 3 ）： 346 - 358 ［ DOI： 10.1504/IJESDF.2021.114956 http://dx.doi.org/10.1504/IJESDF.2021.114956 ］
Shi J ， Xu N ， Zheng H ， Smith A ， Luo J ， and Xu C . SpaceEdit： Learning a unified editing space for open-domain image color editing . In： Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2022 ： 19730 - 19739 ［ DOI： 10.48550/arXiv.2112.00180 http://dx.doi.org/10.48550/arXiv.2112.00180 ］
Song W ， Li S ， Fang L ， and Lu T . Hyperspectral image classification with deep feature fusion network . IEEE Transactions on Geoscience and Remote Sensing ， 2018 ， 56 （ 12 ）： 7103 - 7114 ［ DOI： 10.1109/TGRS.2018.2794326 http://dx.doi.org/10.1109/TGRS.2018.2794326 ］
Tan R T ， Ikeuchi K ， and Nishino K . Color constancy through inverse-intensity chromaticity space . Journal of the Optical Society of America A ， 2004 ， 21 （ 3 ）： 321 - 334 ［ DOI： 10.1364/JOSAA.21.000321 http://dx.doi.org/10.1364/JOSAA.21.000321 ］
Van de Weijer J ， Gevers T ， and Gijsenij A . Edge-based color constancy . IEEE Transactions on Image Processing ， 2007 ， 16 （ 9 ）： 2207 - 2214 ［ DOI： 10.1109/TIP.2007.901808 http://dx.doi.org/10.1109/TIP.2007.901808 ］
Vicente T F Y ， Hoai M ， and Samaras D . Leave-one-out kernel optimization for shadow detection and removal . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2018 ， 40 （ 3 ）： 682 - 695 ［ DOI： 10.1109/TPAMI.2017.2691703 http://dx.doi.org/10.1109/TPAMI.2017.2691703 ］
Wang J ， Wu Z ， Chen J ， Han X ， Shrivastava A ， Lim S N ， and Jiang Y G . ObjectFormer for image manipulation detection and localization . 2022 ［ DOI： 10.48550/arXiv.2203.14681 http://dx.doi.org/10.48550/arXiv.2203.14681 ］
Wang T ， Hu X ， Heng P-A ， and Fu C-W . Instance shadow detection with a single-stage detector . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 2023 ， 45 （ 3 ）： 3259 - 3273 ［ DOI： 10.1109/TPAMI.2022.3185628 http://dx.doi.org/10.1109/TPAMI.2022.3185628 ］
Wang T ， Hu X ， Wang Q ， Heng P-A ， and Fu C-W . Instance shadow detection . In： 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2020 ： 1877 - 1886 ［ DOI： 10.1109/CVPR42600.2020.00195 http://dx.doi.org/10.1109/CVPR42600.2020.00195 ］
Wen B ， Zhu Y ， Subramanian R ， Ng T T ， Shen X ， and Winkler S . COVERAGE — A novel database for copy-move forgery detection . In： 2016 IEEE International Conference on Image Processing （ICIP） . 2016 ： 161 - 165 ［ DOI： 10.1109/ICIP.2016.7532339 http://dx.doi.org/10.1109/ICIP.2016.7532339 ］
Wu Y ， Abd-Almageed W ， and Natarajan P . Image copy-move forgery detection via an end-to-end deep neural network . In： 2018 IEEE Winter Conference on Applications of Computer Vision （WACV） . 2018 ： 363 - 372 ［ DOI： 10.1109/WACV.2018.00211 http://dx.doi.org/10.1109/WACV.2018.00211 ］
Wu Y ， Abdalmageed W ， and Natarajan P . ManTra-Net： Manipulation tracing network for detection and localization of image forgeries with anomalous features . In： 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2019 ： 9535 - 9544 ［ DOI： 10.1109/CVPR.2019.00977 http://dx.doi.org/10.1109/CVPR.2019.00977 ］
Xie S ， Girshick R ， Dollár P ， Tu Z ， and He K . Aggregated residual transformations for deep neural networks . In： 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR） . 2017 ： 5987 - 5995 ［ DOI： 10.1109/CVPR.2017.634 http://dx.doi.org/10.1109/CVPR.2017.634 ］
Xing Z ， Wang T ， Hu X ， Wu H ， Fu C W ， and Heng P A . Video instance shadow detection under the sun and sky . IEEE Transactions on Image Processing ， 2024 ［ DOI： 10.1109/TIP.2024.3468877 http://dx.doi.org/10.1109/TIP.2024.3468877 ］
Ye G ， Wang J ， Yang Z ， Zhang Y ， Cui R ， and Xuan S . Survey of image composition based on deep learning . Journal of Image and Graphics ， 2023 ， 28 （ 12 ）： 3670 - 3698
叶国升 ， 王建明 ， 杨自忠 ， 张宇航 ， 崔荣凯 ， 宣帅 . 2023 . 深度学习图像合成研究综述 . 中国图象图形学报 ， 28 （ 12 ）： 3670 - 3698 ［ DOI： 10.11834/jig.220713 http://dx.doi.org/10.11834/jig.220713 ］
Zhang W ， Cao X ， Zhang J ， Zhu J ， and Wang P . Detecting photographic composites using shadows . In： 2009 IEEE International Conference on Multimedia and Expo （ICME） . 2009 ： 1532 - 1535 ［ DOI： 10.1109/ICME.2009.5202676 http://dx.doi.org/10.1109/ICME.2009.5202676 ］
Zhang Y ， Goh J ， Win L L ， and Thing V . Image region forgery detection： A deep learning approach . In： 2016 International Conference on Digital Image Computing： Techniques and Applications （DICTA） . 2016 ： 1 - 8 ［ DOI： 10.3233/978-1-61499-617-0-1 http://dx.doi.org/10.3233/978-1-61499-617-0-1 ］
Zheng Q ， Qiao X ， Cao Y ， and Lau R W . Distraction-aware shadow detection . In： 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2019 ： 5167 - 5176 ［ DOI： 10.1109/CVPR.2019.00531 http://dx.doi.org/10.1109/CVPR.2019.00531 ］
Zhou J ， Ma X ， Du X ， Khayyat A ， and Feng W . Pre-training-free image manipulation localization through non-mutually exclusive contrastive learning . In： 2023 IEEE/CVF International Conference on Computer Vision （ICCV） . 2023 ［DOI： 10.1109/ICCV51070.2023.02042］
Zhou P ， Han X ， Morariu V I ， and Davis L S . Learning rich features for image manipulation detection . In： 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . 2018 ： 1053 - 1061 ［ DOI： 10.1109/CVPR.2018.00116 http://dx.doi.org/10.1109/CVPR.2018.00116 ］
Zhu Y ， Shen X ， Liu S ， Zhang X ， and Yan G . Image splicing location based on illumination maps and cluster region proposal network . Applied Sciences ， 2021 ， 11 （ 18 ）： 8437 ［ DOI： 10.3390/app11188437 http://dx.doi.org/10.3390/app11188437 ］
相关作者
相关机构
京公网安备11010802024621