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

arXiv: https://arxiv.org/abs/1804.08864 · HTML: https://mlsanity.com/paper/1804.08864/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2018.

## Built on by (most cited first, 30 of 62)

- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Behind the Curtain: Learning Occluded Shapes for 3D Object Detection](https://mlsanity.com/paper/2112.02205/) (2021)
- [Amodal Ground Truth and Completion in the Wild](https://mlsanity.com/paper/2312.17247/) (2023)
- [Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling](https://mlsanity.com/paper/2109.11103/) (2021)
- [Amodal Panoptic Segmentation](https://mlsanity.com/paper/2202.11542/) (2022)
- [AISFormer: Amodal Instance Segmentation with Transformer](https://mlsanity.com/paper/2210.06323/) (2022)
- [Human De-occlusion: Invisible Perception and Recovery for Humans](https://mlsanity.com/paper/2103.11597/) (2021)
- [Occlusion-Aware Video Object Inpainting](https://mlsanity.com/paper/2108.06765/) (2021)
- [Coarse-to-Fine Amodal Segmentation with Shape Prior](https://mlsanity.com/paper/2308.16825/) (2023)
- [E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation](https://mlsanity.com/paper/2203.04074/) (2022)
- [Occlusion Handling in Generic Object Detection: A Review](https://mlsanity.com/paper/2101.08845/) (2021)
- [Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition](https://mlsanity.com/paper/2104.05367/) (2021)
- [A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation](https://mlsanity.com/paper/2108.09897/) (2021)
- [Perceiving the Invisible: Proposal-Free Amodal Panoptic Segmentation](https://mlsanity.com/paper/2205.14637/) (2022)
- [A Tri-Layer Plugin to Improve Occluded Detection](https://mlsanity.com/paper/2210.10046/) (2022)
- [Open-World Amodal Appearance Completion](https://mlsanity.com/paper/2411.13019/) (2024)
- [Image Amodal Completion: A Survey](https://mlsanity.com/paper/2207.02062/) (2022)
- [DoNet: Deep De-overlapping Network for Cytology Instance Segmentation](https://mlsanity.com/paper/2303.14373/) (2023)
- [Object-level Scene Deocclusion](https://mlsanity.com/paper/2406.07706/) (2024)
- [Using Diffusion Priors for Video Amodal Segmentation](https://mlsanity.com/paper/2412.04623/) (2024)
- [Self-supervised Amodal Video Object Segmentation](https://mlsanity.com/paper/2210.12733/) (2022)
- [AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving](https://mlsanity.com/paper/2309.06547/) (2023)
- [Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline](https://mlsanity.com/paper/2206.00527/) (2022)
- [TACO: Taming Diffusion for in-the-wild Video Amodal Completion](https://mlsanity.com/paper/2503.12049/) (2025)
- [Recurrent Generic Contour-based Instance Segmentation with Progressive Learning](https://mlsanity.com/paper/2301.08898/) (2023)
- [BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion](https://mlsanity.com/paper/2401.01642/) (2024)
- [Beyond the Visible: Benchmarking Occlusion Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2508.04059/) (2025)
- [TAO-Amodal: A Benchmark for Tracking Any Object Amodally](https://mlsanity.com/paper/2312.12433/) (2023)
- [Occlusion-Aware Seamless Segmentation](https://mlsanity.com/paper/2407.02182/) (2024)
- [Segment Anything, Even Occluded](https://mlsanity.com/paper/2503.06261/) (2025)

## 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.