mlsanityData to 7 Oct 2026

Instance Shadow Detection

arXiv 1911.07034 ↗First posted 16 Nov 2019cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction. Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results. In our evaluations, we formulate a new metric named the shadow-object average precision to measure the performance of our results. Further, we conducted various experiments and demonstrate our method's applicability on light direction estimation and photo editing.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 8; 2023: 6; 2024: 9; 2025: 5; 2026: 4.

37 papers.

Sort:

By area:

  1. 2024ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertioncited by 71
  2. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  3. 2021From Shadow Generation to Shadow Removalcited by 54
  4. 2021Omnimatte: Associating Objects and Their Effects in Videocited by 50
  5. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  6. 2023A General Protocol to Probe Large Vision Models for 3D Physical Understandingcited by 32
  7. 2025ObjectMover: Generative Object Movement with Video Priorcited by 30
  8. 2023Latent Feature-Guided Diffusion Models for Shadow Removalcited by 28
  9. 2021Learning from Synthetic Shadows for Shadow Detection and Removalcited by 26
  10. 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
  11. 2022SCOTCH and SODA: A Transformer Video Shadow Detection Frameworkcited by 19
  12. 2023SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labelscited by 19
25 more
  1. 2024DepthCues: Evaluating Monocular Depth Perception in Large Vision Modelscited by 18
  2. 2022SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Taskscited by 15
  3. 2023OmnimatteRF: Robust Omnimatte with 3D Background Modelingcited by 14
  4. 2022Casual Indoor HDR Radiance Capture from Omnidirectional Imagescited by 11
  5. 2023SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detectioncited by 11
  6. 2022Learning Shadow Correspondence for Video Shadow Detectioncited by 9
  7. 2022Shadows Shed Light on 3D Objectscited by 8
  8. 2024Language-Driven Interactive Shadow Detectioncited by 7
  9. 2024S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removalcited 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. 2023AdapterShadow: Adapting Segment Anything Model for Shadow Detectioncited by 5
  12. 2024Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentationcited by 5
  13. 2024MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesiscited by 5
  14. 2025Inferring Dynamic Physical Properties from Video Foundation Modelscited by 5
  15. 2022Video Instance Shadow Detection Under the Sun and Skycited by 3
  16. 2025Prompt-Aware Controllable Shadow Removalcited by 2
  17. 2026ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detectioncited by 1
  18. 2022UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removalcited by 0
  19. 2024Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removalcited by 0
  20. 2024RenDetNet: Weakly-supervised Shadow Detection with Shadow Caster Verificationcited by 0
  21. 2025FastInstShadow: A Simple Query-Based Model for Instance Shadow Detectioncited by 0
  22. 2025Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoningcited by 0
  23. 2026LightMover: Generative Light Movement with Color and Intensity Controlscited by 0
  24. 2026PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidancecited by 0
  25. 2026After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Datacited by 0