Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code are available at github.com/grip-unina/DMimageDetection.
FOSCU: Feasibility of Synthetic MRI Generation via Duo-Diffusion Models for Enhancement of 3D U-Nets in Hepatic Segmentation
Seoul National University(首尔国立大学);Sangmyung University(祥明大学);Ewha Womans University(梨花女子大学);Chung-Ang University(中央大学);Samsung Medical Center, Sungkyunkwan University School of Medicine(三星医学中心,成均馆大学医学院);NVIDIA(英伟达)
Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusion
University of Science, VNU-HCM(胡志明市国家大学下属理科大学);Vietnam National University, Ho Chi Minh(胡志明市国家大学);University of Information Technology, VNU-HCM(胡志明市国家大学下属信息技术大学);University of Dayton(代顿大学);National Institute of Informatics(国立信息学研究所)
University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院);Merchants Union Consumer Finance Company(招商局消费金融公司)
3D-LLDM: Label-Guided 3D Latent Diffusion Model for Improving High-Resolution Synthetic MR Imaging in Hepatic Structure Segmentation
OUTTA, Republic of Korea(韩国OUTTA);Stanford University(斯坦福大学);Seoul National University(首尔国立大学);Sangmyung University(Sangmyung大学);Chung-Ang University(Chung-Ang大学);Samsung Medical Center(三星医疗中心);NVIDIA;Sungkyunkwan University School of Medicine(成均馆大学医学院);Samsung Changwon Hospital(三星昌原医院)
Rendering-Refined Stable Diffusion for Privacy Compliant Synthetic Data
University of California, Davis(加利福尼亚大学戴维斯分校);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Australian National University(澳大利亚国立大学);Sony AI, Sony Research(索尼人工智能,索尼研究院)
MAM-E: Mammographic synthetic image generation with diffusion models
Computer Vision and Robotics Institute (ViCOROB), University of Girona(赫罗纳大学计算机视觉与机器人研究所(ViCOROB));Clínica Girona, Institute of Diagnostic Imaging (IDI) Girona, University of Girona(赫罗纳大学赫罗纳诊所诊断影像研究所(IDI))
Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
College of Science and Engineering, University of Galway(戈尔韦大学科学与工程学院);School of Computer Science, University of Galway(戈尔韦大学计算机科学学院);Trinity College Dublin, the University of Dublin(都柏林大学圣三一学院);St James’s Hospital(圣詹姆斯医院)
本文提出 Derm-T2IM,用调优的 Stable Diffusion 生成多样化皮肤镜病变图像,并验证其可增强 CNN 与 ViT 在两个真实数据集上的分类鲁棒性和泛化性。
Synthesizing Diabetic Foot Ulcer Images with Diffusion Model
Institute of Biomedical Engineering, University of Toronto(多伦多大学生物医学工程研究所);University Health Network(多伦多大学健康网络);Zivot Limb Preservation Centre, Peter Lougheed Centre(齐沃特肢体保护中心(彼得·劳埃德中心));Cumming School of Medicine, University of Calgary(卡尔加里大学卡明医学院)
High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology
Chemnitz University of Technology, Chemnitz, Germany(化学工业大学,化学矿泉,德国);Interuniversity Microelectronics Centre (imec), Leuven, Belgium(大学微电子中心(imec),卢汶,比利时)