mlsanityData to 14 Oct 2026

Amodal Ground Truth and Completion in the Wild

arXiv 2312.17247 ↗First posted 28 Dec 2023cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

This paper studies amodal image segmentation: predicting entire object segmentation masks including both visible and invisible (occluded) parts. In previous work, the amodal segmentation ground truth on real images is usually predicted by manual annotaton and thus is subjective. In contrast, we use 3D data to establish an automatic pipeline to determine authentic ground truth amodal masks for partially occluded objects in real images. This pipeline is used to construct an amodal completion evaluation benchmark, MP3D-Amodal, consisting of a variety of object categories and labels. To better handle the amodal completion task in the wild, we explore two architecture variants: a two-stage model that first infers the occluder, followed by amodal mask completion; and a one-stage model that exploits the representation power of Stable Diffusion for amodal segmentation across many categories. Without bells and whistles, our method achieves a new state-of-the-art performance on Amodal segmentation datasets that cover a large variety of objects, including COCOA and our new MP3D-Amodal dataset. The dataset, model, and code are available at https://www.robots.ox.ac.uk/~vgg/research/amodal/.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 39 of its 58 references that are in the map. First posted on arXiv 28 Dec 2023.

Builds on

39 of 58 references.

References · 39

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2023Segment Anythingcited by 8,234
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2017Mask R-CNNcited by 7,277
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  10. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  11. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  12. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
27 more
  1. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  2. 2019The VIA Annotation Software for Images, Audio and Videocited by 167
  3. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  4. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  5. 2015Semantic Amodal Segmentationcited by 103
  6. 2020Self-Supervised Scene De-occlusioncited by 96
  7. 2015Learning to Segment Object Candidatescited by 79
  8. 2016Shape Completion Enabled Robotic Graspingcited by 79
  9. 2016Amodal Instance Segmentationcited by 63
  10. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  11. 2018Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentationcited by 62
  12. 2017SeGAN: Segmenting and Generating the Invisiblecited by 60
  13. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  14. 2020Amodal Segmentation Based on Visible Region Segmentation and Shape Priorcited by 43
  15. 2022Amodal Panoptic Segmentationcited by 38
  16. 2023Amodal Completion via Progressive Mixed Context Diffusioncited by 38
  17. 2022AISFormer: Amodal Instance Segmentation with Transformercited by 35
  18. 2023A General Protocol to Probe Large Vision Models for 3D Physical Understandingcited by 32
  19. 2020Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Modelcited by 29
  20. 2023Coarse-to-Fine Amodal Segmentation with Shape Priorcited by 29
  21. 2019Object-Driven Multi-Layer Scene Decomposition From a Single Imagecited by 26
  22. 2021Visiting the Invisible: Layer-by-Layer Completed Scene Decompositioncited by 23
  23. 2023Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusionscited by 23
  24. 2021A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimationcited by 21
  25. 2022A Tri-Layer Plugin to Improve Occluded Detectioncited by 21
  26. 2023Tracking through Containers and Occluders in the Wildcited by 15
  27. 2019Silhouette Guided Point Cloud Reconstruction beyond Occlusioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 13; 2025: 21; 2026: 11.

45 papers.

Sort:

By area:

  1. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  2. 2024pix2gestalt: Amodal Segmentation by Synthesizing Wholescited by 70
  3. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 54
  4. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 43
  5. 2024Open-World Amodal Appearance Completioncited by 19
  6. 2025HiScene: Creating Hierarchical 3D Scenes with Isometric View Generationcited by 18
  7. 2024Object-level Scene Deocclusioncited by 17
  8. 2024Using Diffusion Priors for Video Amodal Segmentationcited by 16
  9. 2025Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactionscited by 13
  10. 2025LaRender: Training-Free Occlusion Control in Image Generation via Latent Renderingcited by 11
  11. 2024MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenescited by 10
  12. 2025TACO: Taming Diffusion for in-the-wild Video Amodal Completioncited by 10
33 more
  1. 2025DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusioncited by 10
  2. 2025Segment Anything, Even Occludedcited by 7
  3. 2025Inferring Dynamic Physical Properties from Video Foundation Modelscited by 6
  4. 2025GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherencecited by 6
  5. 2024Amodal Instance Segmentation with Diffusion Shape Prior Estimationcited by 5
  6. 2024Amodal Depth Anything: Amodal Depth Estimation in the Wildcited by 5
  7. 2024EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Imagescited by 4
  8. 2026SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generationcited by 4
  9. 2025Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURAcited by 3
  10. 2026EGM: Efficient Visual Grounding Language Modelscited by 3
  11. 2025SynergyAmodal: Deocclude Anything with Text Controlcited by 2
  12. 2025CompleteMe: Reference-based Human Image Completioncited by 2
  13. 2026Amodal SAM: A Unified Amodal Segmentation Framework with Generalizationcited by 2
  14. 2025EscherNet++: Simultaneous Amodal Completion and Scalable View Synthesis through Masked Fine-Tuning and Enhanced Feed-Forward 3D Reconstructioncited by 1
  15. 2025Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpaintingcited by 1
  16. 2025Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusionscited by 1
  17. 2025CObL: Toward Zero-Shot Ordinal Layering without User Promptingcited by 1
  18. 2025Stable Diffusion-Based Approach for Human De-Occlusioncited by 1
  19. 2025GPT-4 for Occlusion Order Recoverycited by 1
  20. 2025ViTA-Seg: Vision Transformer for Amodal Segmentation in Roboticscited by 1
  21. 2024Mask Guided Gated Convolution for Amodal Content Completioncited by 0
  22. 2024Track Anything Behind Everything: Zero-Shot Amodal Video Object Segmentationcited by 0
  23. 2024A2VIS: Amodal-Aware Approach to Video Instance Segmentationcited by 0
  24. 2025R2SM: Referring and Reasoning for Selective Maskscited by 0
  25. 2025Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentationcited by 0
  26. 2026PICS: Pairwise Image Compositing with Spatial Interactionscited by 0
  27. 2026PHAC: Promptable Human Amodal Completioncited by 0
  28. 2026SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Iconscited by 0
  29. 2026Integrating Multimodal Large Language Model Knowledge into Amodal Completioncited by 0
  30. 2026Foreseeing the Invisible: Amodal Reconstruction of Leaf Fossil Imagescited by 0
  31. 2026EgoMaize: A First-Person Maize Instance Segmentation Benchmark under Severe Field Occlusioncited by 0
  32. 2026EVEWorld: Physical Evolution Supervision for Embodied World Modelscited by 0
  33. 2026OccludeBench: Can VLMs Find What's Missing?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Sequential Amodal Segmentation via Cumulative Occlusion Learning
  2. 2025Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation
  3. 2023Completing Visual Objects via Bridging Generation and Segmentation
  4. 2024Fast and Efficient: Mask Neural Fields for 3D Scene Segmentation
  5. 2024MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation
  6. 2023MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
  7. 2024Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing
  8. 2024RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models