mlsanityData to 14 Oct 2026

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

arXiv 2403.10701 ↗First posted 15 Mar 2024cs.CVcited by 64

Not on the map. Why?

Cited by 23 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both view-invariant and conducive to enhanced detail preservation. The subsequent stage leverages this representation to learn seamless harmonization of the object composited to the background. In addition, IMPRINT incorporates a shape-guidance mechanism offering user-directed control over the compositing process. Extensive experiments demonstrate that IMPRINT significantly outperforms existing methods and various baselines on identity preservation and composition quality.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Builds on 53 of its 67 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

53 of 67 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
38 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  2. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  3. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  6. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  7. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  8. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  9. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  10. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  11. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  12. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  13. 2022Blended Latent Diffusioncited by 432
  14. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 412
  15. 2022SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Modelcited by 278
  16. 2018YouTube-VOS: Sequence-to-Sequence Video Object Segmentationcited by 232
  17. 2023HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Modelscited by 225
  18. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  19. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  20. 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Compositioncited by 182
  21. 2023SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Modelscited by 177
  22. 2023Cones: Concept Neurons in Diffusion Models for Customized Generationcited by 150
  23. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  24. 2018ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositingcited by 90
  25. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 77
  26. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  27. 2019Deep Image Blendingcited by 62
  28. 2022Harmonizer: Learning to Perform White-Box Image and Video Harmonizationcited by 61
  29. 2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
  30. 2021PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistencycited by 59
  31. 2023Relightful Harmonization: Lighting-aware Portrait Background Replacementcited by 57
  32. 2023Photoswap: Personalized Subject Swapping in Imagescited by 47
  33. 2022DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonizationcited by 46
  34. 2023ControlCom: Controllable Image Composition using Diffusion Modelcited by 43
  35. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  36. 2020SSN: Soft Shadow Network for Image Compositingcited by 26
  37. 2022Controllable Shadow Generation Using Pixel Height Mapscited by 22
  38. 2020Deep Image Compositingcited by 21

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 18; 2025: 32; 2026: 14.

64 papers.

Sort:

By area:

  1. 2024UniReal: Universal Image Generation and Editing via Learning Real-world Dynamicscited by 102
  2. 2024Zero-shot Image Editing with Reference Imitationcited by 65
  3. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  4. 2025VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Controlcited by 42
  5. 2025OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpaintingcited by 39
  6. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 32
  7. 2024MagicQuill: An Intelligent Interactive Image Editing Systemcited by 30
  8. 2025ObjectMover: Generative Object Movement with Video Priorcited by 30
  9. 2024Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimizationcited by 26
  10. 2024HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awarenesscited by 21
  11. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  12. 2024Magic Insert: Style-Aware Drag-and-Dropcited by 17
38 more
  1. 2025MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Modelscited by 17
  2. 2025MIRA: Multimodal Iterative Reasoning Agent for Image Editingcited by 17
  3. 2024Kubrick: Multimodal Agent Collaborations for Synthetic Video Generationcited by 16
  4. 2024ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generationcited by 16
  5. 2025VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priorscited by 14
  6. 2024GroundingBooth: Grounding Text-to-Image Customizationcited by 13
  7. 20253D-Fixup: Advancing Photo Editing with 3D Priorscited by 12
  8. 2025Flux Already Knows -- Activating Subject-Driven Image Generation without Trainingcited by 11
  9. 2025ORIDa: Object-centric Real-world Image Composition Datasetcited by 11
  10. 2024COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generationcited by 10
  11. 2024TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimizationcited by 9
  12. 2025Multitwine: Multi-Object Compositing with Text and Layout Controlcited by 9
  13. 2024MVOC: a training-free multiple video object composition method with diffusion modelscited by 8
  14. 2024LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generationcited by 8
  15. 2025In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulationcited by 7
  16. 2025BlenderFusion: 3D-Grounded Visual Editing and Generative Compositingcited by 7
  17. 2024Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignmentcited by 5
  18. 2025PIXELS: Progressive Image Xemplar-based Editing with Latent Surgerycited by 5
  19. 2024BIFR"OST: 3D-Aware Image compositing with Language Instructionscited by 4
  20. 2025AIComposer: Any Style and Content Image Composition via Feature Integrationcited by 4
  21. 2025MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cuescited by 4
  22. 2025Interact-Custom: Customized Human Object Interaction Image Generationcited by 3
  23. 2026Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothingcited by 3
  24. 2026Direct 3D-Aware Object Insertion via Decomposed Visual Proxiescited by 3
  25. 2024I2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Mapscited by 2
  26. 2025BlobCtrl: Taming Controllable Blob for Element-level Image Editingcited by 2
  27. 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Modelscited by 2
  28. 2025Learning Joint ID-Textual Representation for ID-Preserving Image Synthesiscited by 2
  29. 2025CompleteMe: Reference-based Human Image Completioncited by 2
  30. 2025MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completioncited by 2
  31. 2025PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinementcited by 2
  32. 2025Geometry-Editable and Appearance-Preserving Object Compositoncited by 1
  33. 2025From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videoscited by 1
  34. 2025PosBridge: Multi-View Positional Embedding Transplant for Identity-Aware Image Editingcited by 1
  35. 2025Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Compositioncited by 1
  36. 2026LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonizationcited by 1
  37. 2026PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectoriescited by 1
  38. 2026Towards Source-Aware Object Swapping with Initial Noise Perturbationcited by 1

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022ObjectStitch: Generative Object Compositing
  2. 2023PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editor
  3. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs
  4. 2025Training-Free Diffusion Framework for Stylized Image Generation with Identity Preservation
  5. 2023Reference-based Image Composition with Sketch via Structure-aware Diffusion Model
  6. 2024FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior
  7. 2025FreeInsert: Personalized Object Insertion with Geometric and Style Control
  8. 2026ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL