# Human De-occlusion: Invisible Perception and Recovery for Humans

arXiv: https://arxiv.org/abs/2103.11597 · HTML: https://mlsanity.com/paper/2103.11597/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 59 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation](https://mlsanity.com/paper/2001.00309/) (2020)
- [Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing](https://mlsanity.com/paper/1703.05446/) (2017)
- [Semantic Amodal Segmentation](https://mlsanity.com/paper/1509.01329/) (2015)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [Devil in the Details: Towards Accurate Single and Multiple Human Parsing](https://mlsanity.com/paper/1809.05996/) (2018)

## Built on by (most cited first, 30 of 31)

- [InsetGAN for Full-Body Image Generation](https://mlsanity.com/paper/2203.07293/) (2022)
- [Amodal Completion via Progressive Mixed Context Diffusion](https://mlsanity.com/paper/2312.15540/) (2023)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal](https://mlsanity.com/paper/2207.11061/) (2022)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Open-World Amodal Appearance Completion](https://mlsanity.com/paper/2411.13019/) (2024)
- [Image Amodal Completion: A Survey](https://mlsanity.com/paper/2207.02062/) (2022)
- [Object-level Scene Deocclusion](https://mlsanity.com/paper/2406.07706/) (2024)
- [Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline](https://mlsanity.com/paper/2206.00527/) (2022)
- [LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering](https://mlsanity.com/paper/2508.07647/) (2025)
- [DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion](https://mlsanity.com/paper/2506.21544/) (2025)
- [CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image](https://mlsanity.com/paper/2503.15671/) (2025)
- [POISE: Pose Guided Human Silhouette Extraction under Occlusions](https://mlsanity.com/paper/2311.05077/) (2023)
- [Synthesizing Environment-Specific People in Photographs](https://mlsanity.com/paper/2312.14579/) (2023)
- [In-Hand 3D Object Reconstruction from a Monocular RGB Video](https://mlsanity.com/paper/2312.16425/) (2023)
- [Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance](https://mlsanity.com/paper/2509.17757/) (2025)
- [Referring Layer Decomposition](https://mlsanity.com/paper/2602.19358/) (2026)
- [Completing Visual Objects via Bridging Generation and Segmentation](https://mlsanity.com/paper/2310.00808/) (2023)
- [Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images](https://mlsanity.com/paper/2407.09694/) (2024)
- [SynergyAmodal: Deocclude Anything with Text Control](https://mlsanity.com/paper/2504.19506/) (2025)
- [CompleteMe: Reference-based Human Image Completion](https://mlsanity.com/paper/2504.20042/) (2025)
- [An Objective Method for Pedestrian Occlusion Level Classification](https://mlsanity.com/paper/2205.05412/) (2022)
- [Amodal Intra-class Instance Segmentation: Synthetic Datasets and Benchmark](https://mlsanity.com/paper/2303.06596/) (2023)
- [DMAT: A Dynamic Mask-Aware Transformer for Human De-occlusion](https://mlsanity.com/paper/2402.04558/) (2024)
- [Stable Diffusion-Based Approach for Human De-Occlusion](https://mlsanity.com/paper/2508.12663/) (2025)
- [Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation](https://mlsanity.com/paper/2512.20936/) (2025)
- [PICS: Pairwise Image Compositing with Spatial Interactions](https://mlsanity.com/paper/2603.06873/) (2026)
- [PHAC: Promptable Human Amodal Completion](https://mlsanity.com/paper/2603.14741/) (2026)
- [CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image](https://mlsanity.com/paper/2603.17779/) (2026)
- [SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons](https://mlsanity.com/paper/2603.24039/) (2026)

## Abstract (arXiv)

In this paper, we tackle the problem of human de-occlusion which reasons about occluded segmentation masks and invisible appearance content of humans. In particular, a two-stage framework is proposed to estimate the invisible portions and recover the content inside. For the stage of mask completion, a stacked network structure is devised to refine inaccurate masks from a general instance segmentation model and predict integrated masks simultaneously. Additionally, the guidance from human parsing and typical pose masks are leveraged to bring prior information. For the stage of content recovery, a novel parsing guided attention module is applied to isolate body parts and capture context information across multiple scales. Besides, an Amodal Human Perception dataset (AHP) is collected to settle the task of human de-occlusion. AHP has advantages of providing annotations from real-world scenes and the number of humans is comparatively larger than other amodal perception datasets. Based on this dataset, experiments demonstrate that our method performs over the state-of-the-art techniques in both tasks of mask completion and content recovery. Our AHP dataset is available at urlhttps://sydney0zq.github.io/ahp/.