mlsanityData to 14 Oct 2026

Instance Shadow Detection with A Single-Stage Detector

arXiv 2207.04614 ↗First posted 11 Jul 2022cs.CV cs.GRcited by 22

Not on the map. Why?

Abstract (arXiv)

This paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image. To approach this task, we first compile a new dataset with the masks for shadow instances, object instances, and shadow-object associations. We then design an evaluation metric for quantitative evaluation of the performance of instance shadow detection. Further, we design a single-stage detector to perform instance shadow detection in an end-to-end manner, where the bidirectional relation learning module and the deformable maskIoU head are proposed in the detector to directly learn the relation between shadow instances and object instances and to improve the accuracy of the predicted masks. Finally, we quantitatively and qualitatively evaluate our method on the benchmark dataset of instance shadow detection and show the applicability of our method on light direction estimation and photo editing.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 46 of its 79 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

46 of 79 references.

References · 46

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2017Mask R-CNNcited by 7,277
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2015Fast R-CNNcited by 2,933
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  7. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  8. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  9. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  10. 2018Path Aggregation Network for Instance Segmentationcited by 798
  11. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
  12. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
34 more
  1. 2020Conditional Convolutions for Instance Segmentationcited by 314
  2. 2019SOLO: Segmenting Objects by Locationscited by 289
  3. 2019Mask Scoring R-CNNcited by 266
  4. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  5. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  6. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
  7. 2020Contextual Residual Aggregation for Ultra High-Resolution Image Inpaintingcited by 124
  8. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 123
  9. 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 121
  10. 2019Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GANcited by 103
  11. 2019TensorMask: A Foundation for Dense Object Segmentationcited by 101
  12. 2019Shadow Removal via Shadow Image Decompositioncited by 98
  13. 2019Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Datacited by 92
  14. 2019SSAP: Single-Shot Instance Segmentation With Affinity Pyramidcited by 85
  15. 2015Learning to Segment Object Candidatescited by 79
  16. 2021Auto-Exposure Fusion for Single-Image Shadow Removalcited by 79
  17. 2016Learning to Refine Object Segmentscited by 67
  18. 2017MegDet: A Large Mini-Batch Object Detectorcited by 66
  19. 2020From Shadow Segmentation to Shadow Removalcited by 59
  20. 2018Direction-aware Spatial Context Features for Shadow Detection and Removalcited by 58
  21. 2017Direction-aware Spatial Context Features for Shadow Detectioncited by 56
  22. 2021From Shadow Generation to Shadow Removalcited by 55
  23. 2017MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Featurescited by 54
  24. 2019ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removalcited by 51
  25. 2020Portrait Shadow Manipulationcited by 42
  26. 2017A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuationcited by 39
  27. 2020Shadow Removal by a Lightness-Guided Network with Training on Unpaired Datacited by 38
  28. 2019Instance Shadow Detectioncited by 37
  29. 2019RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removalcited by 35
  30. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  31. 2019Revisiting Shadow Detection: A New Benchmark Dataset for Complex Worldcited by 34
  32. 2021Triple-cooperative Video Shadow Detectioncited by 22
  33. 2019EmbedMask: Embedding Coupling for One-stage Instance Segmentationcited by 15
  34. 2015Shadow Optimization from Structured Deep Edge Detectioncited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 7; 2025: 7; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for nowcited by 61
  2. 2023SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labelscited by 19
  3. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  4. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  5. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 7
  6. 2025Deep Learning in Concealed Dense Predictioncited by 6
  7. 2023AdapterShadow: Adapting Segment Anything Model for Shadow Detectioncited by 5
  8. 2024Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentationcited by 5
  9. 2024MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesiscited by 5
  10. 2022Video Instance Shadow Detection Under the Sun and Skycited by 3
  11. 2023Structure-Informed Shadow Removal Networkscited by 3
  12. 2023DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generationcited by 3
10 more
  1. 2025Prompt-Aware Controllable Shadow Removalcited by 2
  2. 2024ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow Removalcited by 1
  3. 2025EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decompositioncited by 1
  4. 2024RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verificationcited by 0
  5. 2025FastInstShadow: A Simple Query-Based Model for Instance Shadow Detectioncited by 0
  6. 2025DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removalcited by 0
  7. 2025MultiEditor: Controllable Multimodal Object Editing for Driving Scenarios Using 3D Gaussian Splatting Priorscited by 0
  8. 2025Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoningcited by 0
  9. 2026A Unified and Controllable Framework for Layered Image Generation with Visual Effectscited by 0
  10. 2026MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Modelcited by 0