OverviewDeep learning papers notes sharing, especially for image forgery detection and localization
ccf-rankings now marked with different colors( )
Newly added papers will be organized at the top of every category now.
Related
Basics
Backbone
骨干网络 ,多为图像分类的网络。
Image Tampering
图像篡改检测定位
Image Editing
2025 2024 2023 2022 2021 2020 and beforeCNN-synthesized
Some of the above papers also contain methods to detect tampered images generated by GANs or DMs for synthetic images
Image Splicing
图像的拼接篡改检测定位
2024 2023 2022 2021 2020 and beforeImage Harmonization
图像协调化
Face Forgery
人脸篡改 ,篡改方法以及检测问题
Copy Move
复制移动篡改定位 问题
Image Inpainting
Tamper Text in Detection
图像中的文本篡改检测 问题 (parts of)
Low Level Vision
Related resources:
Low-level tasks include super-resolution, denoise, dehze, low-light enhancement, etc. High-level tasks include classification, detection, segmentation, etc. segmentation, and so on. However, the ones I have listed here are probably still mainly related to tampering detection.
Testing the new layout of paper title.
📖Paper, 👨💻Code, 📦Dataset, 🔗Other links, 📜News,
*Equal contribution. #Corresponding author.
(EVP ) Explicit Visual Prompting for Low-Level Structure Segmentations (CVPR '23 ) 📖 , 👨💻 (including defocus blur, shadow, forgery, camouflaged dection )
Weihuang Liu 1, Xi Shen 2, Chi-Man Pun #,1, Xiaodong Cun #,2
1University of Macau 2Tencent AI Lab
SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device (ICCV '23 ) 📖 , 👨💻
Weiran Gou ∗1,2, Ziyao Yi∗1,2, Yan Xiang1,2, Shaoqing Li1,2, Zibin Liu1,2, Dehui Kong1,2, Ke Xu#1,2
1State Key Laboratory of Mobile Network and Mobile Multimedia Technology, 2Sanechips Technology, Chengdu, China
Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision (ICLR '24_) 📖 , 👨💻
Haoning Wu 1*, Zicheng Zhang 2*, Erli Zhang 1*, Chaofeng Chen 1, Liang Liao 1, Annan Wang 1, Chunyi Li 2, Wenxiu Sun 3, Qiong Yan 3, Guangtao Zhai 2, Weisi Lin 1#
1Nanyang Technological University, 2Shanghai Jiaotong University, 3Sensetime Research
Image Matching
特征匹配 ,图像匹配问题。
Object Detection
目标检测 ,包括伪装物体目标检测和突出目标检测,COD以及SOD。
Semantic Segmentation
语义分割,将图片中完整语义(具有标签或者类别)的部分分割出来。不仅要进行目标检测检测到图像中的物体,还需要对每个像素分类。
Anomaly Detection
异常检测,通常用于发现与正常模式或预期模式不符的图像与视频。
Image Steganography
Useful Links
ICML 2023 https://dblp.org/db/conf/icml/icml2023.html
Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization
SAFIRE: Segment Any Forged Image Region
SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints
Image Forgery Localization with State Space Models
PhotoHolmes: a Python library for forgery detection in digital images
A Novel Universal Image Forensics Localization Model Based on Image Noise and Segment Anything Model
Omni-IML: Towards Unified Image Manipulation Localization
ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
Dual JPEG Compatibility: a Reliable and Explainable Tool for Image Forensics
Is JPEG AI going to change image forensics?
Image Forgery Localization via Guided Noise and Multi-Scale Feature Aggregation
Image manipulation localization via dynamic cross-modality fusion and progressive integration
HRGR: Enhancing Image Manipulation Detection via Hierarchical Region-aware Graph Reasoning
Language-guided Hierarchical Fine-grained Image Forgery Detection and Localization (HiFi-Net++)
Image Manipulation Detection With Implicit Neural Representation and Limited Supervision
AdaIFL: Adaptive Image Forgery Localization via a Dynamic and Importance-aware Transformer Network
Noise-assisted Prompt Learning for Image Forgery Detection and Localization
Learning Universal Features for Generalizable Image Forgery Localization
A Large-scale Interpretable Multi-modality Benchmark for Image Forgery Localization
ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training
ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization
FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
EL-FDL: Improving Image Forgery Detection and Localization via Ensemble Learning
Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation
Detecting and Grounding Multi-Modal Media Manipulation and Beyond
FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection
Auto-focus tracing: Image manipulation detection with artifact graph contrastive
LookupForensics: A Large-Scale Multi-Task Dataset for Multi-Phase Image-Based Fact Verification
Image manipulation detection and localization using multi-scale contrastive learning
Attentive and Contrastive Image Manipulation Localization With Boundary Guidance
Multi-view Feature Extraction via Tunable Prompts is Enough for Image Manipulation Localization
Datasets, Clues and State-of-the-Arts for Multimedia Forensics: An Extensive Review
TGIF: Text-Guided Inpainting Forgery Dataset
Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localization
GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
DH-GAN: Image manipulation localization via a dual homology-aware generative adversarial network
DA-HFNet: Progressive Fine-Grained Forgery Image Detection and Localization Based on Dual Attention
EC-Net: General image tampering localization network based on edge distribution guidance and contrastive learning
Frequency-constrained transferable adversarial attack on image manipulation detection and localization
A Contribution-Aware Noise Feature representation model for image manipulation localization
Effective Image Tampering Localization via Enhanced Transformer and Co-attention Fusion
PROMPT-IML: Image Manipulation Localization with Pre-trained Foundation Models Through Prompt Tuning
Diffusion models meet image counter-forensics
Research about the Ability of LLM in the Tamper-Detection Area
Deep Image Restoration For Image Anti-Forensics
Deep Image Composition Meets Image Forgery
Fusion Transformer with Object Mask Guidance for Image Forgery Analysis (OMG-Fuser)
Exploring Multi-Modal Fusion for Image Manipulation Detection and Localization
A New Benchmark and Model for Challenging Image Manipulation Detection
MGQFormer: Mask-Guided Query-Based Transformer for Image Manipulation Localization
Learning Discriminative Noise Guidance for Image Forgery Detection and Localization
CatmullRom Splines-Based Regression for Image Forgery Localization
UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization
Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods
EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection
DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization
IML-ViT: Image Manipulation Localization by Vision Transformer
CIMGEN: Controlled Image Manipulation by Finetuning Pretrained Generative Models on Limited Data
Image Manipulation Detection Based on Ringed Residual Edge Artifact Enhancement and Multiple Attention Mechanisms
PL-GNet: Pixel Level Global Network for detection and localization of image forgeries
Constrained R-CNN: A general image manipulation detection model [ Paper ] [ Code ]
SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization (ECCV '20 ) [ Paper ] [ Code ]
D-Net: A dual-encoder network for image splicing forgery detection and localization
FD-GAN: Generalizable and Robust Forgery Detection via Generative Adversarial Networks
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
Can We Leave Deepfake Data Behind in Training Deepfake Detector?
Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture
Hierarchical Forgery Classifier On Multi-modality Face Forgery Clues
Identity-Driven Multimedia Forgery Detection via Reference Assistance
Copy-Move Detection in Optical Microscopy: A Segmentation Network and A Dataset
Copy-Move Forgery Detection and Question Answering for Remote Sensing Image
CMCF-Net: An End-to-End Context Multiscale Cross-Fusion Network for Robust Copy-Move Forgery Detection
Wavelet based inpainting detection
Enhanced Wavelet Scattering Network for image inpainting detection
Explainable Tampered Text Detection via Multimodal Large Models
Enhancing Tampered Text Detection through Frequency Feature Fusion and Decomposition
Delving into Adversarial Robustness on Document Tampering Localization
Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning
Generalized Tampered Scene Text Detection in the era of Generative AI
CTP-Net: Character Texture Perception Network for Document Image Forgery Localization (arXiv '23 ) [ Paper ]
Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models
Finding Incompatible Blocks for Reliable JPEG Steganalysis
LiDiNet: A Lightweight Deep Invertible Network for Image-in-Image Steganography
😀