# Peeking into occluded joints: A novel framework for crowd pose estimation

arXiv: https://arxiv.org/abs/2003.10506 · HTML: https://mlsanity.com/paper/2003.10506/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 25 of 25)

- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes](https://mlsanity.com/paper/2104.07300/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images](https://mlsanity.com/paper/2109.05885/) (2021)
- [Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation](https://mlsanity.com/paper/2101.11223/) (2021)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation](https://mlsanity.com/paper/2110.05132/) (2021)
- [Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos](https://mlsanity.com/paper/2207.09425/) (2022)
- [Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity](https://mlsanity.com/paper/2306.07879/) (2023)
- [Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation](https://mlsanity.com/paper/2208.00090/) (2022)
- [Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image](https://mlsanity.com/paper/2302.02410/) (2023)
- [Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision](https://mlsanity.com/paper/2506.06253/) (2025)
- [I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/2206.10892/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation](https://mlsanity.com/paper/2306.17074/) (2023)
- [POISE: Pose Guided Human Silhouette Extraction under Occlusions](https://mlsanity.com/paper/2311.05077/) (2023)
- [LAMP: Leveraging Language Prompts for Multi-person Pose Estimation](https://mlsanity.com/paper/2307.11934/) (2023)
- [DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/2404.14025/) (2024)
- [MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model](https://mlsanity.com/paper/2302.08751/) (2023)
- [GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution](https://mlsanity.com/paper/2409.07752/) (2024)
- [GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network](https://mlsanity.com/paper/2510.07990/) (2025)
- [A comprehensive framework for occluded human pose estimation](https://mlsanity.com/paper/2401.00155/) (2023)
- [Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation](https://mlsanity.com/paper/2504.01298/) (2025)
- [A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network](https://mlsanity.com/paper/2508.11212/) (2025)

## Abstract (arXiv)

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the joints based on visual information; however, the invisible joints are lack of that. In contrast to localization, our framework estimates the invisible joints from an inference perspective by proposing an Image-Guided Progressive GCN module which provides a comprehensive understanding of both image context and pose structure. Moreover, existing benchmarks contain limited occlusions for evaluation. Therefore, we thoroughly pursue this problem and propose a novel OPEC-Net framework together with a new Occluded Pose (OCPose) dataset with 9k annotated images. Extensive quantitative and qualitative evaluations on benchmarks demonstrate that OPEC-Net achieves significant improvements over recent leading works. Notably, our OCPose is the most complex occlusion dataset with respect to average IoU between adjacent instances. Source code and OCPose will be publicly available.