mlsanityData to 7 Oct 2026

Patch-Based Image Inpainting with Generative Adversarial Networks

arXiv 1803.07422 ↗First posted 20 Mar 2018cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

Area of image inpainting over relatively large missing regions recently advanced substantially through adaptation of dedicated deep neural networks. However, current network solutions still introduce undesired artifacts and noise to the repaired regions. We present an image inpainting method that is based on the celebrated generative adversarial network (GAN) framework. The proposed PGGAN method includes a discriminator network that combines a global GAN (G-GAN) architecture with a patchGAN approach. PGGAN first shares network layers between G-GAN and patchGAN, then splits paths to produce two adversarial losses that feed the generator network in order to capture both local continuity of image texture and pervasive global features in images. The proposed framework is evaluated extensively, and the results including comparison to recent state-of-the-art demonstrate that it achieves considerable improvements on both visual and quantitative evaluations.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 16; 2023: 11; 2024: 15; 2025: 6; 2026: 9.

70 papers.

Sort:

By area:

  1. 2024Ovis: Structural Embedding Alignment for Multimodal Large Language Modelcited by 167
  2. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  3. 2021Labels4Free: Unsupervised Segmentation using StyleGANcited by 53
  4. 2022Guided Co-Modulated GAN for 360deg Field of View Extrapolationcited by 32
  5. 2021A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networkscited by 30
  6. 2021Position, Padding and Predictions: A Deeper Look at Position Information in CNNscited by 26
  7. 2021MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GANcited by 14
  8. 2025TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modelingcited by 12
  9. 2022Generative Adversarial Networks for Image Super-Resolution: A Surveycited by 11
  10. 2022Non-Imaging Medical Data Synthesis for Trustworthy AI: A Comprehensive Surveycited by 9
  11. 2022Lip-to-Speech Synthesis for Arbitrary Speakers in the Wildcited by 8
  12. 2023Vision + Language Applications: A Surveycited by 8
38 more
  1. 2023SDF-3DGAN: A 3D Object Generative Method Based on Implicit Signed Distance Functioncited by 7
  2. 2023RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognitioncited by 7
  3. 2021Generative Adversarial Networks for Synthetic Data Generation: A Comparative Studycited by 5
  4. 2022CS2: A Controllable and Simultaneous Synthesizer of Images and Annotations with Minimal Human Interventioncited by 5
  5. 2021Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised Learningcited by 4
  6. 2022Convolutional Neural Processes for Inpainting Satellite Imagescited by 4
  7. 2022Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Processcited by 4
  8. 2023PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpaintingcited by 4
  9. 2023CryoGEM: Physics-Informed Generative Cryo-Electron Microscopycited by 4
  10. 2024Zero-shot Text-guided Infinite Image Synthesis with LLM guidancecited by 4
  11. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 4
  12. 2022HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysiscited by 3
  13. 2022BSDGAN: Balancing Sensor Data Generative Adversarial Networks for Human Activity Recognitioncited by 3
  14. 2021Diverse Single Image Generation with Controllable Global Structurecited by 2
  15. 2022GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservationcited by 2
  16. 2022Faster Diffusion Cardiac MRI with Deep Learning-based breath hold reductioncited by 2
  17. 2023Leveraging Activation Maximization and Generative Adversarial Training to Recognize and Explain Patterns in Natural Areas in Satellite Imagerycited by 2
  18. 2023Dynamic Appearance Modeling of Clothed 3D Human Avatars using a Single Cameracited by 2
  19. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  20. 2025Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancementscited by 2
  21. 2025MRIQT: Physics-Aware Diffusion Model for Image Quality Transfer in Neonatal Ultra-Low-Field MRIcited by 2
  22. 2021Neural Relighting and Expression Transfer On Video Portraitscited by 1
  23. 2021Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approachcited by 1
  24. 2022Region-aware Attention for Image Inpaintingcited by 1
  25. 2022Face editing with GAN -- A Reviewcited by 1
  26. 2023Reconstructing Existing Levels through Level Inpaintingcited by 1
  27. 2024Seeing Through the Clouds: Cloud Gap Imputation with Prithvi Foundation Modelcited by 1
  28. 2024HSFusion: A high-level vision task-driven infrared and visible image fusion network via semantic and geometric domain transformationcited by 1
  29. 2024Learning-Based WiFi Fingerprint Inpainting via Generative Adversarial Networkscited by 1
  30. 2024A Comprehensive Survey on Synthetic Infrared Image synthesiscited by 1
  31. 2025CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesiscited by 1
  32. 2025Galaxy image simplification using Generative AIcited by 1
  33. 2025Base Station Deployment under EMF constrain by Deep Reinforcement learningcited by 1
  34. 2026CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantizationcited by 1
  35. 2026Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolutioncited by 1
  36. 2021Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus diseasecited by 0
  37. 2021Generative Residual Attention Network for Disease Detectioncited by 0
  38. 2021Unsupervised Image to Image Translation for Multiple Retinal Pathology Synthesis in Optical Coherence Tomography Scanscited by 0

50 most cited of 70 All 70 (JSON)