mlsanityData to 14 Oct 2026

ObjectStitch: Generative Object Compositing

arXiv 2212.00932 ↗First posted 2 Dec 2022cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore, annotating training data pairs for compositing requires substantial manual effort from professionals, and is hardly scalable. Thus, with the recent advances in generative models, in this work, we propose a self-supervised framework for object compositing by leveraging the power of conditional diffusion models. Our framework can hollistically address the object compositing task in a unified model, transforming the viewpoint, geometry, color and shadow of the generated object while requiring no manual labeling. To preserve the input object's characteristics, we introduce a content adaptor that helps to maintain categorical semantics and object appearance. A data augmentation method is further adopted to improve the fidelity of the generator. Our method outperforms relevant baselines in both realism and faithfulness of the synthesized result images in a user study on various real-world images.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 42 of its 52 references that are in the map. First posted on arXiv 2 Dec 2022.

Builds on

42 of 52 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2022Generative Adversarial Networkscited by 5,627
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  11. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  12. 2021Zero-Shot Text-to-Image Generationcited by 4,288
30 more
  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  7. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  8. 2015Spatial Transformer Networkscited by 1,429
  9. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  10. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  11. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  13. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 212
  14. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  15. 2017Deep Image Mattingcited by 150
  16. 2016Deep Image Homography Estimationcited by 136
  17. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 135
  18. 2021Vision Transformer for Small-Size Datasetscited by 122
  19. 2017Deep Image Harmonizationcited by 120
  20. 2022ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Expertscited by 112
  21. 2018ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositingcited by 90
  22. 2019Rendering Synthetic Objects into Legacy Photographscited by 72
  23. 2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
  24. 2016Deep Outdoor Illumination Estimationcited by 53
  25. 2020BargainNet: Background-Guided Domain Translation for Image Harmonizationcited by 52
  26. 2022DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonizationcited by 46
  27. 2019Automatic Scene Inference for 3D Object Compositingcited by 36
  28. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  29. 2020SSN: Soft Shadow Network for Image Compositingcited by 26
  30. 2022Controllable Shadow Generation Using Pixel Height Mapscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 13; 2024: 11; 2025: 9; 2026: 3.

36 papers.

Sort:

By area:

  1. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 304
  2. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 231
  3. 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Compositioncited by 182
  4. 2023Inst-Inpaint: Instructing to Remove Objects with Diffusion Modelscited by 66
  5. 2023ControlCom: Controllable Image Composition using Diffusion Modelcited by 43
  6. 2025VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Controlcited by 42
  7. 2023Collage Diffusioncited by 33
  8. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 32
  9. 2025UniCombine: Unified Multi-Conditional Combination with Diffusion Transformercited by 26
  10. 2023Diffusion-based Document Layout Generationcited by 21
  11. 2024PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steeringcited by 20
  12. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
24 more
  1. 2023PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editorcited by 17
  2. 2023DreamCom: Finetuning Text-guided Inpainting Model for Image Compositioncited by 17
  3. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  4. 2024FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correctioncited by 17
  5. 2024Magic Insert: Style-Aware Drag-and-Dropcited by 17
  6. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  7. 2024GroundingBooth: Grounding Text-to-Image Customizationcited by 13
  8. 2023Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanitiescited by 9
  9. 2025Multitwine: Multi-Object Compositing with Text and Layout Controlcited by 9
  10. 2024Scaling Concept With Text-Guided Diffusion Modelscited by 8
  11. 2025PairEdit: Learning Semantic Variations for Exemplar-based Image Editingcited by 8
  12. 2023ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNetcited by 7
  13. 2024Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesiscited by 7
  14. 2025BlenderFusion: 3D-Grounded Visual Editing and Generative Compositingcited by 7
  15. 2023Scene-Conditional 3D Object Stylization and Compositioncited by 4
  16. 2024Foodfusion: A Novel Approach for Food Image Composition via Diffusion Modelscited by 4
  17. 2024MureObjectStitch: Multi-reference Image Compositioncited by 4
  18. 2023Animating Street Viewcited by 3
  19. 2025Diffusion Models are Secretly Zero-Shot 3DGS Harmonizerscited by 2
  20. 2025Single Image Iterative Subject-driven Generation and Editingcited by 0
  21. 2025Borrowing from anything: A generalizable framework for reference-guided instance editingcited by 0
  22. 2026OSInsert: Towards High-authenticity and High-fidelity Image Compositioncited by 0
  23. 2026MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Modelcited by 0
  24. 2026Lighting-Consistent Object Transfer Across Radiance Fieldscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation
  2. 2026PICS: Pairwise Image Compositing with Spatial Interactions
  3. 2024IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation
  4. 2023Cross-domain Compositing with Pretrained Diffusion Models
  5. 2026Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing
  6. 2026PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories
  7. 2025gen2seg: Generative Models Enable Generalizable Instance Segmentation
  8. 2023ObjectComposer: Consistent Generation of Multiple Objects Without Fine-tuning