# 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information

arXiv: https://arxiv.org/abs/1608.03075 · HTML: https://mlsanity.com/paper/1608.03075/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2016.

## Built on by (most cited first, 28 of 28)

- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [DiffPose: Toward More Reliable 3D Pose Estimation](https://mlsanity.com/paper/2211.16940/) (2022)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [EventHPE: Event-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2108.06819/) (2021)
- [D&D: Learning Human Dynamics from Dynamic Camera](https://mlsanity.com/paper/2209.08790/) (2022)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)
- [KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2404.00658/) (2024)
- [HMP: Hand Motion Priors for Pose and Shape Estimation from Video](https://mlsanity.com/paper/2312.16737/) (2023)
- [PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2101.02471/) (2021)
- [Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation](https://mlsanity.com/paper/2303.04991/) (2023)
- [Human Pose and Shape Estimation from Single Polarization Images](https://mlsanity.com/paper/2108.06834/) (2021)
- [Self-supervised 3D Human Pose Estimation from a Single Image](https://mlsanity.com/paper/2304.02349/) (2023)
- [Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions](https://mlsanity.com/paper/2103.03170/) (2021)
- [Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input](https://mlsanity.com/paper/2312.06797/) (2023)
- [Heuristic Weakly Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2105.10996/) (2021)
- [V-VIPE: Variational View Invariant Pose Embedding](https://mlsanity.com/paper/2407.07092/) (2024)
- [TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video](https://mlsanity.com/paper/2105.06599/) (2021)
- [3D Human Scan With A Moving Event Camera](https://mlsanity.com/paper/2404.08504/) (2024)
- [Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2405.17016/) (2024)
- [On the role of depth predictions for 3D human pose estimation](https://mlsanity.com/paper/2103.02521/) (2021)
- [Iterative Graph Filtering Network for 3D Human Pose Estimation](https://mlsanity.com/paper/2307.16074/) (2023)
- [Multi-hop graph transformer network for 3D human pose estimation](https://mlsanity.com/paper/2405.03055/) (2024)
- [Flexible graph convolutional network for 3D human pose estimation](https://mlsanity.com/paper/2407.19077/) (2024)
- [Age-Inclusive 3D Human Mesh Recovery for Action-Preserving Data Anonymization](https://mlsanity.com/paper/2512.05259/) (2025)
- [Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment](https://mlsanity.com/paper/2404.09499/) (2024)
- [Object Agnostic 3D Lifting in Space and Time](https://mlsanity.com/paper/2412.01166/) (2024)
- [Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors](https://mlsanity.com/paper/2507.12336/) (2025)
- [Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation](https://mlsanity.com/paper/2511.08809/) (2025)

## Abstract (arXiv)

While there has been a success in 2D human pose estimation with convolutional neural networks (CNNs), 3D human pose estimation has not been thoroughly studied. In this paper, we tackle the 3D human pose estimation task with end-to-end learning using CNNs. Relative 3D positions between one joint and the other joints are learned via CNNs. The proposed method improves the performance of CNN with two novel ideas. First, we added 2D pose information to estimate a 3D pose from an image by concatenating 2D pose estimation result with the features from an image. Second, we have found that more accurate 3D poses are obtained by combining information on relative positions with respect to multiple joints, instead of just one root joint. Experimental results show that the proposed method achieves comparable performance to the state-of-the-art methods on Human 3.6m dataset.