mlsanityData to 7 Oct 2026

Shadow Generation for Composite Image in Real-world Scenes

arXiv 2104.10338 ↗First posted 21 Apr 2021cs.CV eess.IVcited by 35

Not on the map. Why?

Abstract (arXiv)

Image composition targets at inserting a foreground object into a background image. Most previous image composition methods focus on adjusting the foreground to make it compatible with background while ignoring the shadow effect of foreground on the background. In this work, we focus on generating plausible shadow for the foreground object in the composite image. First, we contribute a real-world shadow generation dataset DESOBA by generating synthetic composite images based on paired real images and deshadowed images. Then, we propose a novel shadow generation network SGRNet, which consists of a shadow mask prediction stage and a shadow filling stage. In the shadow mask prediction stage, foreground and background information are thoroughly interacted to generate foreground shadow mask. In the shadow filling stage, shadow parameters are predicted to fill the shadow area. Extensive experiments on our DESOBA dataset and real composite images demonstrate the effectiveness of our proposed method. Our dataset and code are available at https://github.com/bcmi/Object-Shadow-Generation-Dataset-DESOBA.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 21 Apr 2021.

Builds on

32 of 54 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  9. 2018cGANs with Projection Discriminatorcited by 253
  10. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  11. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
  12. 2017Deep Image Harmonizationcited by 120
20 more
  1. 2019Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANcited by 102
  2. 2019Shadow Removal via Shadow Image Decompositioncited by 96
  3. 2019Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Datacited by 91
  4. 2018ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositingcited by 90
  5. 2019Deep Parametric Indoor Lighting Estimationcited by 82
  6. 2019Improving the Harmony of the Composite Image by Spatial-Separated Attention Modulecited by 73
  7. 2018Spatial Fusion GAN for Image Synthesiscited by 68
  8. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  9. 2019Deep Image Blendingcited by 62
  10. 2020From Shadow Segmentation to Shadow Removalcited by 59
  11. 2015Learning a Discriminative Model for the Perception of Realism in Composite Imagescited by 52
  12. 2020BargainNet: Background-Guided Domain Translation for Image Harmonizationcited by 52
  13. 2019All-Weather Deep Outdoor Lighting Estimationcited by 41
  14. 2019Instance Shadow Detectioncited by 37
  15. 2019Automatic Scene Inference for 3D Object Compositingcited by 36
  16. 2019RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removalcited by 35
  17. 2018Conditional Image-to-Image Translationcited by 30
  18. 2020Adversarial Image Composition with Auxiliary Illuminationcited by 21
  19. 2020Deep Image Compositingcited by 21
  20. 2020Towards Realistic 3D Embedding via View Alignmentcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 9; 2024: 9; 2025: 5; 2026: 5.

35 papers.

Sort:

By area:

  1. 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Compositioncited by 182
  2. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
  3. 2024IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representationcited by 64
  4. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  5. 2022ObjectStitch: Generative Object Compositingcited by 36
  6. 2023Collage Diffusioncited by 33
  7. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  8. 2023Latent Feature-Guided Diffusion Models for Shadow Removalcited by 28
  9. 2024Tuning-Free Image Customization with Image and Text Guidancecited by 25
  10. 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
  11. 2022Controllable Shadow Generation Using Pixel Height Mapscited by 22
  12. 2022Learning Object Placement via Dual-path Graph Completioncited by 20
23 more
  1. 2024PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steeringcited by 20
  2. 2023DreamCom: Finetuning Text-guided Inpainting Model for Image Compositioncited by 17
  3. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  4. 2024ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generationcited by 16
  5. 2023Cross-domain Compositing with Pretrained Diffusion Modelscited by 13
  6. 2022Fast Object Placement Assessmentcited by 12
  7. 2025ORIDa: Object-centric Real-world Image Composition Datasetcited by 11
  8. 2024Single-Image Shadow Removal Using Deep Learning: A Comprehensive Surveycited by 7
  9. 2023Foreground Object Search by Distilling Composite Image Featurecited by 6
  10. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 6
  11. 2024MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesiscited by 5
  12. 2023Structure-Informed Shadow Removal Networkscited by 3
  13. 2023DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generationcited by 3
  14. 2023Animating Street Viewcited by 3
  15. 2022Spatial Transformation for Image Composition via Correspondence Learningcited by 2
  16. 2025Refracting Reality: Generating Images with Realistic Transparent Objectscited by 2
  17. 2025FastInstShadow: A Simple Query-Based Model for Instance Shadow Detectioncited by 0
  18. 2025Embedding Physical Reasoning into Diffusion-Based Shadow Generation Under the Sun and Skycited by 0
  19. 2026Joint Shadow Generation and Relighting via Light-Geometry Interaction Mapscited by 0
  20. 2026MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Modelcited by 0
  21. 2026VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusioncited by 0
  22. 2026Revisiting Shadow Detection from a Vision-Language Perspectivecited by 0
  23. 2026Hybrid Generative-Discriminative Object Placementcited by 0