mlsanityData to 7 Oct 2026

EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning

arXiv 1901.00212 ↗First posted 1 Jan 2019cs.CVcited by 161

Not on the map. Why?

Abstract (arXiv)

Over the last few years, deep learning techniques have yielded significant improvements in image inpainting. However, many of these techniques fail to reconstruct reasonable structures as they are commonly over-smoothed and/or blurry. This paper develops a new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details. We propose a two-stage adversarial model EdgeConnect that comprises of an edge generator followed by an image completion network. The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori. We evaluate our model end-to-end over the publicly available datasets CelebA, Places2, and Paris StreetView, and show that it outperforms current state-of-the-art techniques quantitatively and qualitatively. Code and models available at: https://github.com/knazeri/edge-connect

Key facts. Cited by 161 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 42; 2023: 37; 2024: 23; 2025: 9; 2026: 5.

161 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  3. 2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Modelscited by 323
  4. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  5. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 219
  6. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  7. 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
  8. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 168
  9. 2023Flow Matching in Latent Spacecited by 155
  10. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  11. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  12. 2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
38 more
  1. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  2. 2021Diverse Image Inpainting with Bidirectional and Autoregressive Transformerscited by 80
  3. 2021PD-GAN: Probabilistic Diverse GAN for Image Inpaintingcited by 80
  4. 2023Residual Denoising Diffusion Modelscited by 68
  5. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  6. 2023Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Modelcited by 60
  7. 2022CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Trainingcited by 49
  8. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  9. 2023Designing a Better Asymmetric VQGAN for StableDiffusioncited by 45
  10. 2021WaveFill: A Wavelet-based Generation Network for Image Inpaintingcited by 44
  11. 2022NeRF-In: Free-Form NeRF Inpainting with RGB-D Priorscited by 43
  12. 2021Finding and Fixing Spurious Patterns with Explanationscited by 38
  13. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 37
  14. 2021Image Inpainting by End-to-End Cascaded Refinement with Mask Awarenesscited by 35
  15. 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
  16. 2023CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Queryingcited by 34
  17. 2023Pixel-Inconsistency Modeling for Image Manipulation Localizationcited by 33
  18. 2024DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detectioncited by 33
  19. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  20. 2021SketchEdit: Mask-Free Local Image Manipulation with Partial Sketchescited by 32
  21. 2021Learning by Planning: Language-Guided Global Image Editingcited by 25
  22. 2022Keys to Better Image Inpainting: Structure and Texture Go Hand in Handcited by 25
  23. 2023DiffI2I: Efficient Diffusion Model for Image-to-Image Translationcited by 24
  24. 2024ScribbleLight: Single Image Indoor Relighting with Scribblescited by 22
  25. 2021Image Inpainting with External-internal Learning and Monochromic Bottleneckcited by 21
  26. 2023Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videoscited by 21
  27. 2021Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesiscited by 20
  28. 2023Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Modelcited by 20
  29. 2021Internal Video Inpainting by Implicit Long-range Propagationcited by 19
  30. 2021Free-form tumor synthesis in computed tomography images via richer generative adversarial networkcited by 16
  31. 2021Detailed Avatar Recovery from Single Imagecited by 16
  32. 2023KD-DLGAN: Data Limited Image Generation via Knowledge Distillationcited by 16
  33. 2021TrajeVAE: Controllable Human Motion Generation from Trajectoriescited by 14
  34. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  35. 2022Volumetric Disentanglement for 3D Scene Manipulationcited by 13
  36. 2023Learning Image-Adaptive Codebooks for Class-Agnostic Image Restorationcited by 13
  37. 2022DeViT: Deformed Vision Transformers in Video Inpaintingcited by 12
  38. 2023RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detectioncited by 12

50 most cited of 161 All 161 (JSON)