Newly added papers will be organized at the top of every category now.

• Datasets Resources
• Nice Expression
• Research Methods (public information summery)
• Paper Resource Links

• 图像处理基础知识

骨干网络，多为图像分类的网络。

• Attention Is All You Need (NeurIPS '17) [Paper] [Code_official] [Code_community]
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (ICML '19) [Paper] [Code]
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ICLR '21) [Paper] [Code]
• Multi-Dimensional Model Compression of Vision Transformer (ICME '22) [Paper]
• Deep Residual Learning for Image Recognition (CVPR '16) [Paper]
• Generative Adversarial Networks (NeurIPS '14) [Paper]
• Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond (CVPR '23) [Paper]
• A Kernel Perspective of Skip Connections in Convolutional Networks (ICLR '23) [Paper]
• EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention (CVPR '23) [Paper] [Code] [Note_community]
• Vision Transformers Need Registers (ICLR '24) [Paper]

图像篡改检测定位

Some of the above papers also contain methods to detect tampered images generated by GANs or DMs for synthetic images

• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection (CVPR '24) [Paper]
• Preserving Fairness Generalization in Deepfake Detection (CVPR '24) [Paper] [Code]
• Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection (arXiv '24) [Paper] [Code]
• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection (arXiv '23) [Paper]
• AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors (arXiv '23) [Paper] [Code]
• MaLP: Manipulation Localization Using a Proactive Scheme (CVPR '23) [Paper] [Code]
• Discrepancy-Guided Reconstruction Learning for Image Forgery Detection (IJCAI '23) [Paper] [Code]
• Generalizable Synthetic Image Detection via Language-guided Contrastive Learning (arXiv '23) [Paper] [Code]
• Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization (arXiv '23) [Paper] [Code]
• Discrepancy-Guided Reconstruction Learning for Image Forgery Detection (arXiv '23) [Paper]
• Masked Relation Learning for DeepFake Detection (TIFS '23) [Paper]

图像的拼接篡改检测定位

图像协调化

• Toward Realistic Image Compositing with Adversarial Learning (CVPR '19) [Paper] [Code_unofficial]
• Image Harmonization with Transformer (ICCV '21) [Paper]
• SSH: A Self-Supervised Framework for Image Harmonization (ICCV '21) [Paper] [Code]
• Image Harmonization with Region-wise Contrastive Learning (ArXiv '22) [Paper]
• Harmonizer: Learning to Perform White-Box Image and Video Harmonization (ECCV '22) [Paper] [Code]
• Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization (ECCV '22) [Paper] [Code]
• High-Resolution Image Harmonization via Collaborative Dual Transformations (CVPR '22) [Paper] [Code_unofficial]
• SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization (CVPR '22) [Paper] [Code]
• PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations (CVPR '23)
• Semi-supervised Parametric Real-world Image Harmonization (CVPR '23) [Paper] [Code] [Project]
• LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization(CVPR '23) [Paper]
• Burstormer: Burst Image Restoration and Enhancement Transformer (CVPR '23) [Paper] [Code]

人脸篡改，篡改方法以及检测问题

• MCS-GAN: A Different Understanding for Generalization of Deep Forgery Detection (TMM '23) [Paper]
• Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection (AAAI '24) [Paper] [Code]
• Contrastive Learning for DeepFake Classification and Localization via Multi-Label Ranking (CVPR '24)
• Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection (CVPR '24) [Paper]
• Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection (ICLR '24) [Paper] [Code]
• Improving Fairness in Deepfake Detection (WACV '24) [Paper] [Code]
• Weakly-Supervised Deepfake Localization in Diffusion-Generated Images (WACV '24) [Paper] [Code]
• Controllable Guide-Space for Generalizable Face Forgery Detection (ICCV '23) [Paper]
• RAIRNet: Region-Aware Identity Rectification for Face Forgery Detection (MM '23) [Paper]
• Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation (ICCV '23) [Paper] [Code]
• UCF: Uncovering Common Features for Generalizable Deepfake Detection (ICCV '23) [Paper]
• Learning Patch-Channel Correspondence for Interpretable Face Forgery Detection (TIP '23) [Paper] [Code]
• Contrastive Multi-FaceForensics: An End-to-end Bi-grained Contrastive Learning Approach for Multi-face Forgery Detection (arXiv '23') [Paper]
• Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection (arXiv '23') [Paper]
• AUNet: Learning Relations Between Action Units for Face Forgery Detection (CVPR '23) [Paper]
• AltFreezing for More General Face Forgery Detection (CVPR '23) [Paper] **[Code]88
• $F^2$Trans: High-Frequency Fine-Grained Transformer for Face Forgery Detection (TIFS '23) [Paper]
• On the Security of the One-and-a-Half-Class Classifier for SPAM Feature-Based Image Forensics (TIFS '23) [Paper]
• Multimodaltrace: Deepfake Detection Using Audiovisual Representation Learning (CVPRW '23) [Paper]
• MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection (KBS '22) [Paper]
• Multi-Scale Wavelet Transformer for Face Forgery Detection (ACCV '22) [Paper]
• Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection (CVPR '22) [Paper] [Code]
• SSTNet: Detecting Manipulated Faces Through Spatial, Steganalysis and Temporal Features (ICASSP '20) [Paper]
• Portrait shadow manipulation (ACM MM / TOG '20) [Paper] [Code]

复制移动篡改定位问题

• Robust Image Hashing via CP Decomposition and DCT for Copy Detection (TOMM '24) [Paper]
• Lightweight and High-Precision Network for Image Copy-Move Forgery Detection (SPL '24) [Paper]
• Advancing Copy-Move Manipulation Detection in Complex Image Scenarios Through Multiscale Detector (IEEE Access ‘24) [Paper]
• Cascaded Adaptive Graph Representation Learning for Image Copy-Move Forgery Detection (TOMM '24) [Paper]
• Image Copy-Move Forgery Detection and Localization Scheme: How to Avoid Missed Detection and False Alarm (arXiv '24) [Paper] [Code]
• Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning (arXiv '24) [Paper]
• Object-level Copy-Move Forgery Image Detection based on Inconsistency Mining (WWW '24) [Paper]
• UCM-Net: A U-Net-Like Tampered-Region-Related Framework for Copy-Move Forgery Detection (TMM '24) [Paper]
• An effective image copy-move forgery detection using entropy image (arXiv '23) [Paper]
• CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning (arXiv '23) [Paper]
• An approach for copy-move image multiple forgery detection based on an optimized pre-trained deep learning model (KBS '23) [Paper]
• Image Copy-Move Forgery Detection via Deep Cross-Scale PatchMatch (ICME '23) [Paper]
• BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization (ECCV '18) [Paper] [Code]
• A Serial Image Copy-Move Forgery Localization Scheme With Source/Target Distinguishment (TMM '20) [Paper] [Code]
• DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization (CVPR '20) [Paper] [Code]
• Two-Stage Copy-Move Forgery Detection with Self Deep Matching and Proposal SuperGlue (TIP '22) [Paper]
• QDL-CMFD: A Quality-independent and deep Learning-based Copy-Move image forgery detection method (Neurocomputing '22) [Paper] [Code]
• Shrinking the Semantic Gap: Spatial Pooling of Local Moment Invariants for Copy-Move Forgery Detection (TIFS '23) [Paper] [Code]

图像中的文本篡改检测问题 (parts of)

• A Two-Stage Dual-Path Framework for Text Tampering Detection and Recognition (arXiv '24) [Paper]
• Toward Real Text Manipulation Detection: New Dataset and New Solution (arXiv '23) [Paper] [Code]
• Towards Robust Tampered Text Detection in Document Image: New dataset and New Solution (CVPR '23) [Paper] [Code]
• Progressive Supervision for Tampering Localization in Document Images (ICONIP '23) [Paper]
• SigScatNet: A Siamese + Scattering based Deep Learning Approach for Signature Forgery Detection and Similarity Assessment (arXiv '23) [Paper]
• Image Generation and Learning Strategy for Deep Document Forgery Detection (arXiv '23) [Paper]
• Forgery-free signature verification with stroke-aware cycle-consistent generative adversarial network (Neurocomputing '22) [Paper] [Code]
• Document Forgery Detection in the Context of Double JPEG Compression (ICPR '22) [Paper]

Related resources:

• https://github.com/Kobaayyy/Awesome-ICCV2021-Low-Level-Vision
• https://github.com/lcybuzz/Low-Level-Vision-Paper-Record

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 Liu¹, Xi Shen², 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 Xiang^1,2, Shaoqing Li^1,2, Zibin Liu^1,2, Dehui Kong^1,2, 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 Chen¹, Liang Liao¹, Annan Wang¹, Chunyi Li², Wenxiu Sun³, Qiong Yan³, Guangtao Zhai², Weisi Lin^1#

  ¹Nanyang Technological University, ²Shanghai Jiaotong University, ³Sensetime Research

特征匹配，图像匹配问题。

• FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer(arXiv '23) [Paper]
• LoFTR: Detector-Free Local Matching with Transformers (CVPR '21) [Paper] [Code]
• PATS: Patch Area Transportation with Subdivision for Local Feature Matching (CVPR '23) [Paper] [Code] [Project]
• Adaptive Spot-Guided Transformer for Consistent Local Feature Matching (CVPR '23) [Paper] [Code] [Project]
• ObjectMatch: Robust Registration using Canonical Object Correspondences (CVPR '23) [Paper] [Code] [Project]

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。

• HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping (AAAI '24) [Paper]
• Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection (CVPR '24)
• VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning (CVPR '24) [Paper]
• Weakly Supervised Open-Vocabulary Object Detection (AAAI '24) [Paper]
• OTA: Optimal Transport Assignment for Object Detection (CVPR '21) [Paper] [Code]
• Consistency-basd Active Learning for Object Detection (CVPRW '22) [Paper] [Code]
• Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (CVPR '22) [Paper] [Code]
• Unsupervised Object Localization: Observing the Background to Discover Objects (CVPR '23) [Paper] [Code]
• Camouflaged Object Detection with Feature Decomposition and Edge Reconstruction (CVPR '23) [Paper] [Code]
• Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers (CVPR '23) [Paper] [Code]
• Locate, Refine and Restore: A Progressive Enhancement Network for Camouflaged Object Detection (IJCAI '23) [Paper]
• Spatial-Aware Token for Weakly Supervised Object Localization (ICCV '23) [Paper] [Code]
• Generative Prompt Model for Weakly Supervised Object Localization (ICCV '23) [Paper] [Code]
• Category-aware Allocation Transformer for Weakly Supervised Object Localization (ICCV '23) [Paper]

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。

• Generative Semantic Segmentation (CVPR '23) [Paper] [Code]
• EfficientViT: Lightweight Multi-Scale Attention for On-Device Semantic Segmentation [Paper] [Code]
• CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation [Paper] [Code] [Project] [Note_community**]

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。

• Contextual Affinity Distillation for Image Anomaly Detection (WACV '24) [Paper]
• PromptAD: Zero-Shot Anomaly Detection Using Text Prompts (WACV '24) [Paper]
• Holistic Representation Learning for Multitask Trajectory Anomaly Detection (WACV '24) [Paper] [Code]

1. IJCAI 2024 Main Track Accepted Papers https://ijcai24.org/main-track-accepted-papers/
2. CVPR 2024 Accepted Papers https://cvpr2023.thecvf.com/Conferences/2024/AcceptedPapers
3. ICLR 2024 Papers List https://openreview.net/group?id=ICLR.cc/2024/Conference
4. WACV 2024 Papers https://openaccess.thecvf.com/WACV2024
5. MM 2023 Proceedings https://dl.acm.org/doi/proceedings/10.1145/3581783
6. ICML 2023 https://dblp.org/db/conf/icml/icml2023.html
7. ICCV 2023 Paper List https://huggingface.co/spaces/ICCV2023/ICCV2023-papers
8. AAAI 2023 https://dblp.org/db/conf/aaai/aaai2023.html
9. ECCV 2022 Accepted papers https://eccv2022.ecva.net/program/accepted-papers/
10. SIGGRAPH unofficial https://kesen.realtimerendering.com/ eg SIGGRAPH 2023 https://kesen.realtimerendering.com/sig2023.html
11. TIFS https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=10206
12. More...