mlsanityData to 14 Oct 2026

Image Inpainting for Irregular Holes Using Partial Convolutions

arXiv 1804.07723 ↗First posted 20 Apr 2018cs.CVcited by 505

Not on the map. Why?

Cited by 43 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value). This often leads to artifacts such as color discrepancy and blurriness. Post-processing is usually used to reduce such artifacts, but are expensive and may fail. We propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with other methods to validate our approach.

Key facts. Cited by 505 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 125; 2022: 136; 2023: 89; 2024: 72; 2025: 51; 2026: 32.

505 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  2. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  3. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  4. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  5. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 635
  6. 2022Visual Prompting via Image Inpaintingcited by 250
  7. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 220
  8. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 218
  9. 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
  10. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  11. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  12. 2022FILM: Frame Interpolation for Large Motioncited by 153
38 more
  1. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  2. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  3. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 130
  4. 2021Pathdreamer: A World Model for Indoor Navigationcited by 118
  5. 2021Counterfactual Generative Networkscited by 111
  6. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEcited by 106
  7. 2022ConvMAE: Masked Convolution Meets Masked Autoencoderscited by 105
  8. 2021FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpaintingcited by 95
  9. 2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
  10. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  11. 2022Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encodingcited by 83
  12. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  13. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  14. 2021Diverse Image Inpainting with Bidirectional and Autoregressive Transformerscited by 80
  15. 2021PD-GAN: Probabilistic Diverse GAN for Image Inpaintingcited by 80
  16. 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
  17. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
  18. 2023HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Modelscited by 67
  19. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 67
  20. 2021Image Inpainting via Conditional Texture and Structure Dual Generationcited by 66
  21. 2022Removing Objects From Neural Radiance Fieldscited by 66
  22. 2023Inst-Inpaint: Instructing to Remove Objects with Diffusion Modelscited by 66
  23. 2021PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifiercited by 65
  24. 2022Ghost-free High Dynamic Range Imaging with Context-aware Transformercited by 65
  25. 2024Zero-shot Image Editing with Reference Imitationcited by 65
  26. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  27. 2021InfinityGAN: Towards Infinite-Pixel Image Synthesiscited by 61
  28. 2023Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Modelscited by 61
  29. 2023Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Modelcited by 60
  30. 2022Flow-Guided Transformer for Video Inpaintingcited by 59
  31. 2023RealFill: Reference-Driven Generation for Authentic Image Completioncited by 59
  32. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  33. 2022Dialog Inpainting: Turning Documents into Dialogscited by 56
  34. 2021In&Out : Diverse Image Outpainting via GAN Inversioncited by 55
  35. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 54
  36. 2023Putting People in Their Place: Affordance-Aware Human Insertion into Scenescited by 53
  37. 2021Diverse Semantic Image Synthesis via Probability Distribution Modelingcited by 49
  38. 2022CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Trainingcited by 49

50 most cited of 505 All 505 (JSON)