mlsanityData to 13 Oct 2026

Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation

arXiv 1804.08864 ↗First posted 24 Apr 2018cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Semantic amodal segmentation is a recently proposed extension to instance-aware segmentation that includes the prediction of the invisible region of each object instance. We present the first all-in-one end-to-end trainable model for semantic amodal segmentation that predicts the amodal instance masks as well as their visible and invisible part in a single forward pass. In a detailed analysis, we provide experiments to show which architecture choices are beneficial for an all-in-one amodal segmentation model. On the COCO amodal dataset, our model outperforms the current baseline for amodal segmentation by a large margin. To further evaluate our model, we provide two new datasets with ground truth for semantic amodal segmentation, D2S amodal and COCOA cls. For both datasets, our model provides a strong baseline performance. Using special data augmentation techniques, we show that amodal segmentation on D2S amodal is possible with reasonable performance, even without providing amodal training data.

Key facts. Cited by 62 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 9; 2022: 9; 2023: 9; 2024: 17; 2025: 13; 2026: 5.

62 papers.

Sort:

By area:

  1. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  2. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  3. 2023Amodal Ground Truth and Completion in the Wildcited by 44
  4. 2021Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modelingcited by 43
  5. 2022Amodal Panoptic Segmentationcited by 37
  6. 2022AISFormer: Amodal Instance Segmentation with Transformercited by 35
  7. 2021Human De-occlusion: Invisible Perception and Recovery for Humanscited by 31
  8. 2021Occlusion-Aware Video Object Inpaintingcited by 30
  9. 2023Coarse-to-Fine Amodal Segmentation with Shape Priorcited by 29
  10. 2022E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentationcited by 27
  11. 2021Occlusion Handling in Generic Object Detection: A Reviewcited by 25
  12. 2021Visiting the Invisible: Layer-by-Layer Completed Scene Decompositioncited by 23
38 more
  1. 2021A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimationcited by 21
  2. 2022A Tri-Layer Plugin to Improve Occluded Detectioncited by 21
  3. 2022Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentationcited by 20
  4. 2022Image Amodal Completion: A Surveycited by 18
  5. 2024Open-World Amodal Appearance Completioncited by 18
  6. 2023DoNet: Deep De-overlapping Network for Cytology Instance Segmentationcited by 17
  7. 2024Object-level Scene Deocclusioncited by 17
  8. 2024Using Diffusion Priors for Video Amodal Segmentationcited by 16
  9. 2022Self-supervised Amodal Video Object Segmentationcited by 14
  10. 2023AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Drivingcited by 13
  11. 2022Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baselinecited by 12
  12. 2025TACO: Taming Diffusion for in-the-wild Video Amodal Completioncited by 10
  13. 2023Recurrent Generic Contour-based Instance Segmentation with Progressive Learningcited by 9
  14. 2024BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansioncited by 9
  15. 2025Beyond the Visible: Benchmarking Occlusion Perception in Multimodal Large Language Modelscited by 8
  16. 2023TAO-Amodal: A Benchmark for Tracking Any Object Amodallycited by 7
  17. 2025Segment Anything, Even Occludedcited by 7
  18. 2024ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentationcited by 6
  19. 2024Occlusion-Aware Seamless Segmentationcited by 6
  20. 2022Occlusion-Aware Instance Segmentation via BiLayer Network Architecturescited by 5
  21. 2024Amodal Instance Segmentation with Diffusion Shape Prior Estimationcited by 5
  22. 2023Neural Textured Deformable Meshes for Robust Analysis-by-Synthesiscited by 4
  23. 2024PLUG: Revisiting Amodal Segmentation with Foundation Model and Hierarchical Focuscited by 4
  24. 2021Amodal segmentation just like doing a jigsawcited by 3
  25. 2024WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusioncited by 3
  26. 2025Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURAcited by 3
  27. 2025Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentationcited by 3
  28. 2024GAInS: Gradient Anomaly-aware Biomedical Instance Segmentationcited by 2
  29. 2025SynergyAmodal: Deocclude Anything with Text Controlcited by 2
  30. 2026Amodal SAM: A Unified Amodal Segmentation Framework with Generalizationcited by 2
  31. 2023Amodal Intra-class Instance Segmentation: Synthetic Datasets and Benchmarkcited by 1
  32. 2023SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenescited by 1
  33. 2024Sequential Amodal Segmentation via Cumulative Occlusion Learningcited by 1
  34. 2024Hyper-Transformer for Amodal Completioncited by 1
  35. 2024Foundation Models for Amodal Video Instance Segmentation in Automated Drivingcited by 1
  36. 2025Training for X-Ray Vision: Amodal Segmentation, Amodal Content Completion, and View-Invariant Object Representation from Multi-Camera Videocited by 1
  37. 2025Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusionscited by 1
  38. 2025CObL: Toward Zero-Shot Ordinal Layering without User Promptingcited by 1

50 most cited of 62 All 62 (JSON)