# Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

arXiv: https://arxiv.org/abs/2108.07181 · HTML: https://mlsanity.com/paper/2108.07181/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera](https://mlsanity.com/paper/1705.01583/) (2017)
- [2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning](https://mlsanity.com/paper/1802.09232/) (2018)
- [Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1912.06971/) (2019)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [Exploiting temporal information for 3D pose estimation](https://mlsanity.com/paper/1711.08585/) (2017)
- [Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2007.14690/) (2020)
- [Spatial Temporal Transformer Network for Skeleton-based Action Recognition](https://mlsanity.com/paper/2012.06399/) (2020)
- [Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching](https://mlsanity.com/paper/1911.04131/) (2019)
- [Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade](https://mlsanity.com/paper/1704.01344/) (2017)
- [Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation](https://mlsanity.com/paper/1908.08289/) (2019)
- [OriNet: A Fully Convolutional Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1811.04989/) (2018)
- [Mix Dimension in Poincar'e Geometry for 3D Skeleton-based Action Recognition](https://mlsanity.com/paper/2007.15678/) (2020)

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

- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling](https://mlsanity.com/paper/2204.13686/) (2022)
- [HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation](https://mlsanity.com/paper/2304.04269/) (2023)
- [P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.07628/) (2022)
- [SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos](https://mlsanity.com/paper/2112.13715/) (2021)
- [Learning Discriminative Representations for Skeleton Based Action Recognition](https://mlsanity.com/paper/2303.03729/) (2023)
- [GFPose: Learning 3D Human Pose Prior with Gradient Fields](https://mlsanity.com/paper/2212.08641/) (2022)
- [SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling](https://mlsanity.com/paper/2303.17368/) (2023)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition](https://mlsanity.com/paper/2210.07503/) (2022)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos](https://mlsanity.com/paper/2404.04430/) (2024)
- [MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls](https://mlsanity.com/paper/2407.21136/) (2024)
- [HDFormer: High-order Directed Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.01825/) (2023)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation](https://mlsanity.com/paper/2206.06420/) (2022)
- [Cross-Modal Learning with 3D Deformable Attention for Action Recognition](https://mlsanity.com/paper/2212.05638/) (2022)
- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation](https://mlsanity.com/paper/2311.12028/) (2023)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2212.04761/) (2022)
- [Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting](https://mlsanity.com/paper/2402.18330/) (2024)
- [Hierarchical Graph Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.11927/) (2021)
- [Regular Splitting Graph Network for 3D Human Pose Estimation](https://mlsanity.com/paper/2305.05785/) (2023)
- [A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation](https://mlsanity.com/paper/2311.03312/) (2023)
- [HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation](https://mlsanity.com/paper/2301.07322/) (2023)
- [ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting](https://mlsanity.com/paper/2307.09026/) (2023)
- [HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.14581/) (2023)

## Abstract (arXiv)

Various deep learning techniques have been proposed to solve the single-view 2D-to-3D pose estimation problem. While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory. In this work, we target these hard poses and present a novel skeletal GNN learning solution. To be specific, we propose a hop-aware hierarchical channel-squeezing fusion layer to effectively extract relevant information from neighboring nodes while suppressing undesired noises in GNN learning. In addition, we propose a temporal-aware dynamic graph construction procedure that is robust and effective for 3D pose estimation. Experimental results on the Human3.6M dataset show that our solution achieves 10.3% average prediction accuracy improvement and greatly improves on hard poses over state-of-the-art techniques. We further apply the proposed technique on the skeleton-based action recognition task and also achieve state-of-the-art performance. Our code is available at https://github.com/ailingzengzzz/Skeletal-GNN.