mlsanityData to 7 Oct 2026

Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

arXiv 2108.12947 ↗First posted 30 Aug 2021eess.IV cs.CV cs.LGcited by 78

Not on the map. Why?

Abstract (arXiv)

Detecting and localizing image manipulation are necessary to counter malicious use of image editing techniques. Accordingly, it is essential to distinguish between authentic and tampered regions by analyzing intrinsic statistics in an image. We focus on JPEG compression artifacts left during image acquisition and editing. We propose a convolutional neural network (CNN) that uses discrete cosine transform (DCT) coefficients, where compression artifacts remain, to localize image manipulation. Standard CNNs cannot learn the distribution of DCT coefficients because the convolution throws away the spatial coordinates, which are essential for DCT coefficients. We illustrate how to design and train a neural network that can learn the distribution of DCT coefficients. Furthermore, we introduce Compression Artifact Tracing Network (CAT-Net) that jointly uses image acquisition artifacts and compression artifacts. It significantly outperforms traditional and deep neural network-based methods in detecting and localizing tampered regions.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 15 of its 73 references that are in the map. First posted on arXiv 30 Aug 2021.

Builds on

15 of 73 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  7. 2020Media Forensics and DeepFakes: an overviewcited by 208
  8. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  9. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  10. 2018Noiseprint: a CNN-based camera model fingerprintcited by 114
  11. 2020SPAN: Spatial Pyramid Attention Network forImage Manipulation Localizationcited by 92
  12. 2017Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networkscited by 22
3 more
  1. 2019A Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detectioncited by 15
  2. 2020Deep Convolutional Neural Network for Identifying Seam-Carving Forgerycited by 9
  3. 2020Block-level Double JPEG Compression Detection for Image Forgery Localizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 15; 2024: 18; 2025: 25; 2026: 16.

78 papers.

Sort:

By area:

  1. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  2. 2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
  3. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
  4. 2023AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensicscited by 46
  5. 2023IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformercited by 42
  6. 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localizationcited by 42
  7. 2023Pixel-Inconsistency Modeling for Image Manipulation Localizationcited by 33
  8. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  9. 2023Toward Real Text Manipulation Detection: New Dataset and New Solutioncited by 20
  10. 2024TGIF: Text-Guided Inpainting Forgery Datasetcited by 20
  11. 2024GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localizationcited by 19
  12. 2024DeCLIP: Decoding CLIP representations for deepfake localizationcited by 17
38 more
  1. 2024Language-guided Hierarchical Fine-grained Image Forgery Detection and Localizationcited by 16
  2. 2023Effective Image Tampering Localization via Enhanced Transformer and Co-attention Fusioncited by 15
  3. 2024Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localizationcited by 15
  4. 2023Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clusteringcited by 12
  5. 2023UPOCR: Towards Unified Pixel-Level OCR Interfacecited by 12
  6. 2023Multi-spectral Class Center Network for Face Manipulation Detection and Localizationcited by 11
  7. 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detectioncited by 11
  8. 2023DRAW: Defending Camera-shooted RAW against Image Manipulationcited by 10
  9. 2025SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpaintingcited by 10
  10. 2024Evolution of Detection Performance throughout the Online Lifespan of Synthetic Imagescited by 8
  11. 2024ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Trainingcited by 8
  12. 2024Fusion Transformer with Object Mask Guidance for Image Forgery Analysiscited by 7
  13. 2024Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localizationcited by 7
  14. 2025Common Inpainted Objects In-N-Out of Contextcited by 7
  15. 2026Venus-DeFakerOne: Unified Fake Image Detection & Localizationcited by 7
  16. 2023Diffusion models meet image counter-forensicscited by 6
  17. 2025ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attackcited by 6
  18. 2023MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localizationcited by 5
  19. 2024Detecting AI-Generated Images via CLIPcited by 5
  20. 2022Effective Image Tampering Localization with Multi-Scale ConvNeXt Feature Fusioncited by 4
  21. 2023Progressive Feedback-Enhanced Transformer for Image Forgery Localizationcited by 4
  22. 2025AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Eracited by 4
  23. 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Modelscited by 4
  24. 2025Vision-Language Model Guided Image Restorationcited by 4
  25. 2022SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localizationcited by 3
  26. 2024PROMPT-IML: Image Manipulation Localization with Pre-trained Foundation Models Through Prompt Tuningcited by 3
  27. 2024Dense Feature Interaction Network for Image Inpainting Localizationcited by 3
  28. 2025Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotationcited by 3
  29. 2025Revisiting Image Manipulation Localization under Realistic Manipulation Scenarioscited by 3
  30. 2025DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted Baselinecited by 3
  31. 2023Transferable Adversarial Attack on Image Tampering Localizationcited by 2
  32. 2024Deep Image Composition Meets Image Forgerycited by 2
  33. 2024Image Forgery Localization with State Space Modelscited by 2
  34. 2025A Lightweight and Effective Image Tampering Localization Network with Vision Mambacited by 2
  35. 2025DF2023: The Digital Forensics 2023 Dataset for Image Forgery Detectioncited by 2
  36. 2025Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localizationcited by 2
  37. 2026Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstructioncited by 2
  38. 2024HRGR: Enhancing Image Manipulation Detection via Hierarchical Region-aware Graph Reasoningcited by 1

50 most cited of 78 All 78 (JSON)