mlsanityData to 14 Oct 2026

Deep Image Harmonization

arXiv 1703.00069 ↗First posted 28 Feb 2017cs.CVcited by 120

Not on the map. Why?

Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have focused on learning statistical relationships between hand-crafted appearance features of the foreground and background, which is unreliable especially when the contents in the two layers are vastly different. In this work, we propose an end-to-end deep convolutional neural network for image harmonization, which can capture both the context and semantic information of the composite images during harmonization. We also introduce an efficient way to collect large-scale and high-quality training data that can facilitate the training process. Experiments on the synthesized dataset and real composite images show that the proposed network outperforms previous state-of-the-art methods.

Key facts. Cited by 120 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 21; 2022: 35; 2023: 28; 2024: 13; 2025: 13; 2026: 10.

120 papers.

Sort:

By area:

  1. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  2. 2021GAN Inversion: A Surveycited by 367
  3. 2022ARF: Artistic Radiance Fieldscited by 147
  4. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  5. 2024Transparent Image Layer Diffusion using Latent Transparencycited by 114
  6. 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
  7. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  8. 2022Harmonizer: Learning to Perform White-Box Image and Video Harmonizationcited by 61
  9. 2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
  10. 2023Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generationcited by 60
  11. 2023Relightful Harmonization: Lighting-aware Portrait Background Replacementcited by 57
  12. 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
38 more
  1. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  2. 2022DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonizationcited by 46
  3. 2023ControlCom: Controllable Image Composition using Diffusion Modelcited by 43
  4. 2025OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpaintingcited by 39
  5. 2022ObjectStitch: Generative Object Compositingcited by 36
  6. 2023Neural Preset for Color Style Transfercited by 36
  7. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  8. 2021Contrastive Representation Learning for Hand Shape Estimationcited by 34
  9. 2022Probabilistic Compositional Embeddings for Multimodal Image Retrievalcited by 29
  10. 2021OPA: Object Placement Assessment Datasetcited by 28
  11. 2023Semi-supervised Parametric Real-world Image Harmonizationcited by 26
  12. 2021Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonizationcited by 25
  13. 2022SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonizationcited by 24
  14. 2023Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Modelcited by 21
  15. 2022Learning Object Placement via Dual-path Graph Completioncited by 20
  16. 2023Dense Pixel-to-Pixel Harmonization via Continuous Image Representationcited by 19
  17. 2023Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistencycited by 19
  18. 2022Image Amodal Completion: A Surveycited by 18
  19. 2023NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objectscited by 17
  20. 2023DreamCom: Finetuning Text-guided Inpainting Model for Image Compositioncited by 17
  21. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  22. 2025IntrinsicEdit: Precise generative image manipulation in intrinsic spacecited by 17
  23. 2023Integrating View Conditions for Image Synthesiscited by 16
  24. 2024Geometry Transfer for Stylizing Radiance Fieldscited by 16
  25. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  26. 2023PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositingcited by 15
  27. 2021Visible Watermark Removal via Self-calibrated Localization and Background Refinementcited by 14
  28. 2023Cross-domain Compositing with Pretrained Diffusion Modelscited by 13
  29. 2024Open-Set Domain Adaptation for Semantic Segmentationcited by 13
  30. 2022Fast Object Placement Assessmentcited by 12
  31. 2022Hierarchical Dynamic Image Harmonizationcited by 12
  32. 2023LEMaRT: Label-Efficient Masked Region Transform for Image Harmonizationcited by 12
  33. 2023Deep Image Harmonization in Dual Color Spacescited by 12
  34. 2025Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonizationcited by 12
  35. 2021Deep Image Harmonization by Bridging the Reality Gapcited by 11
  36. 2022Painterly Image Harmonization in Dual Domainscited by 11
  37. 2026DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancercited by 10
  38. 2022Deep Video Harmonization with Color Mapping Consistencycited by 9

50 most cited of 120 All 120 (JSON)