mlsanityData to 7 Oct 2026

RealFill: Reference-Driven Generation for Authentic Image Completion

arXiv 2309.16668 ↗First posted 28 Sep 2023cs.CV cs.AI cs.GRcited by 58

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Builds on 43 of its 60 references that are in the map. First posted on arXiv 28 Sep 2023.

Builds on

43 of 60 references.

References · 43

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  12. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
31 more
  1. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  2. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  3. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  4. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  5. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  6. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  7. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  9. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  10. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  11. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  12. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  13. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  14. 2023Emergent Correspondence from Image Diffusioncited by 437
  15. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  16. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generationcited by 300
  17. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  18. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  19. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  20. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 230
  21. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 229
  22. 2023HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Modelscited by 224
  23. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  24. 2023Subject-driven Text-to-Image Generation via Apprenticeship Learningcited by 210
  25. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
  26. 2019Pluralistic Image Completioncited by 162
  27. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  28. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71
  29. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  30. 2023Designing a Better Asymmetric VQGAN for StableDiffusioncited by 45
  31. 2022GeoFill: Reference-Based Image Inpainting with Better Geometric Understandingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 24; 2025: 21; 2026: 5.

58 papers.

Sort:

By area:

  1. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  2. 2024Improving Diffusion Models for Authentic Virtual Try-on in the Wildcited by 109
  3. 2024UniReal: Universal Image Generation and Editing via Learning Real-world Dynamicscited by 100
  4. 2024Controllable Generation with Text-to-Image Diffusion Models: A Surveycited by 82
  5. 2024ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuningcited by 68
  6. 2024Zero-shot Image Editing with Reference Imitationcited by 64
  7. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 63
  8. 2023NeRFiller: Completing Scenes via Generative 3D Inpaintingcited by 62
  9. 2023Readout Guidance: Learning Control from Diffusion Featurescited by 52
  10. 2024RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Controlcited by 46
  11. 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcingcited by 37
  12. 2024Identity Decoupling for Multi-Subject Personalization of Text-to-Image Modelscited by 33
38 more
  1. 2024Photorealistic Object Insertion with Diffusion-Guided Inverse Renderingcited by 27
  2. 2024RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpaintingcited by 21
  3. 2025AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpaintingcited by 21
  4. 2023CLiC: Concept Learning in Contextcited by 20
  5. 2024Taming Latent Diffusion Model for Neural Radiance Field Inpaintingcited by 20
  6. 2024Magic Insert: Style-Aware Drag-and-Dropcited by 17
  7. 2025MangaNinja: Line Art Colorization with Precise Reference Followingcited by 17
  8. 2025RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priorscited by 17
  9. 2023Generate E-commerce Product Background by Integrating Category Commonality and Personalized Stylecited by 16
  10. 2024PuzzleAvatar: Assembling 3D Avatars from Personal Albumscited by 16
  11. 2023Generative Powers of Tencited by 15
  12. 2024PFStorer: Personalized Face Restoration and Super-Resolutioncited by 13
  13. 2024GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splattingcited by 13
  14. 2025DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspectioncited by 12
  15. 2025IMFine: 3D Inpainting via Geometry-guided Multi-view Refinementcited by 10
  16. 2025Follow-Your-Color: Multi-Instance Sketch Colorizationcited by 10
  17. 2025UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collectionscited by 10
  18. 2025LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removalcited by 9
  19. 2025CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion Modelscited by 8
  20. 2024Sp2360: Sparse-view 360 Scene Reconstruction using Cascaded 2D Diffusion Priorscited by 7
  21. 2024NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editingcited by 7
  22. 2025PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Modelscited by 7
  23. 2025RGB-to-Polarization Estimation: A New Task and Benchmark Studycited by 6
  24. 2024Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignmentcited by 5
  25. 2024NeRF-Insert: 3D Local Editing with Multimodal Control Signalscited by 4
  26. 2024Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpaintingcited by 4
  27. 2025RewardSDS: Aligning Score Distillation via Reward-Weighted Samplingcited by 4
  28. 2025GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completioncited by 4
  29. 2023Personalized Restoration via Dual-Pivot Tuningcited by 3
  30. 2024Survey of User Interface Design and Interaction Techniques in Generative AI Applicationscited by 3
  31. 2024Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Datacited by 3
  32. 2025Seeing Beyond Haze: Generative Nighttime Image Dehazingcited by 3
  33. 2024GroupDiff: Diffusion-based Group Portrait Editingcited by 2
  34. 2025Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Modelscited by 2
  35. 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infillingcited by 2
  36. 2026Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Modelscited by 1
  37. 2026GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Secondscited by 1
  38. 2024FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Imagecited by 0

50 most cited of 58 All 58 (JSON)