mlsanityData to 7 Oct 2026

Pluralistic Image Completion

arXiv 1903.04227 ↗First posted 11 Mar 2019cs.CVcited by 162

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for pluralistic image completion -- the task of generating multiple and diverse plausible solutions for image completion. A major challenge faced by learning-based approaches is that usually only one ground truth training instance per label. As such, sampling from conditional VAEs still leads to minimal diversity. To overcome this, we propose a novel and probabilistically principled framework with two parallel paths. One is a reconstructive path that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution. The other is a generative path for which the conditional prior is coupled to the distribution obtained in the reconstructive path. Both are supported by GANs. We also introduce a new short+long term attention layer that exploits distant relations among decoder and encoder features, improving appearance consistency. When tested on datasets with buildings (Paris), faces (CelebA-HQ), and natural images (ImageNet), our method not only generated higher-quality completion results, but also with multiple and diverse plausible outputs.

Key facts. Cited by 162 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 43; 2023: 38; 2024: 29; 2025: 10; 2026: 5.

162 papers.

Sort:

By area:

  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  2. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  3. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  4. 2023TextDiffuser: Diffusion Models as Text Painterscited by 223
  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. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusioncited by 200
  8. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  9. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  10. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEcited by 106
  11. 2021Variational Relational Point Completion Networkcited by 103
  12. 2021Diverse Image Inpainting with Bidirectional and Autoregressive Transformerscited by 80
38 more
  1. 2021PD-GAN: Probabilistic Diverse GAN for Image Inpaintingcited by 80
  2. 2023Monte Carlo guided Diffusion for Bayesian linear inverse problemscited by 65
  3. 2023Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Modelscited by 61
  4. 2023RealFill: Reference-Driven Generation for Authentic Image Completioncited by 58
  5. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  6. 2023PanoDiffusion: 360-degree Panorama Outpainting via Diffusioncited by 50
  7. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  8. 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
  9. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  10. 2021Bridging Global Context Interactions for High-Fidelity Image Completioncited by 40
  11. 2023Reference-guided Controllable Inpainting of Neural Radiance Fieldscited by 40
  12. 2024Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpaintingcited by 40
  13. 2022Reduce Information Loss in Transformers for Pluralistic Image Inpaintingcited by 36
  14. 2021Image Inpainting by End-to-End Cascaded Refinement with Mask Awarenesscited by 35
  15. 2024BrushEdit: All-In-One Image Inpainting and Editingcited by 31
  16. 2022Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fieldscited by 29
  17. 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
  18. 2021BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learningcited by 26
  19. 2021Conditional Image Generation by Conditioning Variational Auto-Encoderscited by 25
  20. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  21. 2022GLF-CR: SAR-Enhanced Cloud Removal with Global-Local Fusioncited by 24
  22. 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
  23. 2021Visiting the Invisible: Layer-by-Layer Completed Scene Decompositioncited by 23
  24. 2023Image Inpainting via Tractable Steering of Diffusion Modelscited by 22
  25. 2023Improving Cross-modal Alignment for Text-Guided Image Inpaintingcited by 21
  26. 2021Stroke-Based Scene Text Erasing Using Synthetic Data for Trainingcited by 20
  27. 2022Partially Does It: Towards Scene-Level FG-SBIR with Partial Inputcited by 20
  28. 2022N"UWA-LIP: Language Guided Image Inpainting with Defect-free VQGANcited by 19
  29. 2022Image Amodal Completion: A Surveycited by 18
  30. 2022Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contextcited by 18
  31. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  32. 2023Pluralistic Aging Diffusion Autoencodercited by 17
  33. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  34. 2024DeCLIP: Decoding CLIP representations for deepfake localizationcited by 17
  35. 2024Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysiscited by 15
  36. 2021TrajeVAE: Controllable Human Motion Generation from Trajectoriescited by 14
  37. 2021PanoDR: Spherical Panorama Diminished Reality for Indoor Scenescited by 13
  38. 2021Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networkscited by 13

50 most cited of 162 All 162 (JSON)