# Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

arXiv: https://arxiv.org/abs/2012.11806 · HTML: https://mlsanity.com/paper/2012.11806/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 23 of 23)

- [Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2206.12126/) (2022)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2404.00658/) (2024)
- [PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos](https://mlsanity.com/paper/2404.04430/) (2024)
- [ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics](https://mlsanity.com/paper/2106.01981/) (2021)
- [Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks](https://mlsanity.com/paper/2104.01797/) (2021)
- [Dual networks based 3D Multi-Person Pose Estimation from Monocular Video](https://mlsanity.com/paper/2205.00748/) (2022)
- [RAM: Recover Any 3D Human Motion in-the-Wild](https://mlsanity.com/paper/2603.19929/) (2026)
- [HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2503.23331/) (2025)
- [NIMBLE: A Non-rigid Hand Model with Bones and Muscles](https://mlsanity.com/paper/2202.04533/) (2022)
- [Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet](https://mlsanity.com/paper/2207.04320/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework](https://mlsanity.com/paper/2203.04113/) (2022)
- [CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods](https://mlsanity.com/paper/2508.18753/) (2025)
- [3D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN Refinement](https://mlsanity.com/paper/2404.16136/) (2024)
- [Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2405.17016/) (2024)
- [BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustment](https://mlsanity.com/paper/2410.20731/) (2024)
- [Deep Neural Networks in Video Human Action Recognition: A Review](https://mlsanity.com/paper/2305.15692/) (2023)
- [Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation](https://mlsanity.com/paper/2207.07900/) (2022)
- [Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2309.01365/) (2023)
- [Behavior Imitation for Manipulator Control and Grasping with Deep Reinforcement Learning](https://mlsanity.com/paper/2405.01284/) (2024)
- [HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation](https://mlsanity.com/paper/2505.04276/) (2025)
- [Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation](https://mlsanity.com/paper/2511.19542/) (2025)

## Abstract (arXiv)

Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and inaccurate person detection. To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters. In particular, we introduce a human-joint GCN, which, unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results. We also introduce a human-bone GCN, which models the bone connections and provides more information beyond human joints. The two GCNs work together to estimate the spatial frame-wise 3D poses and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information. To further refine the 3D pose estimation, we use our temporal convolutional networks (TCNs) to enforce the temporal and human-dynamics constraints. We use a joint-TCN to estimate person-centric 3D poses across frames, and propose a velocity-TCN to estimate the speed of 3D joints to ensure the consistency of the 3D pose estimation in consecutive frames. Finally, to estimate the 3D human poses for multiple persons, we propose a root-TCN that estimates camera-centric 3D poses without requiring camera parameters. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method.