# 3D Human Pose Estimation with 2D Marginal Heatmaps

arXiv: https://arxiv.org/abs/1806.01484 · HTML: https://mlsanity.com/paper/1806.01484/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2018.

## Built on by (most cited first, 20 of 20)

- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation](https://mlsanity.com/paper/2105.02465/) (2021)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [Lifting Monocular Events to 3D Human Poses](https://mlsanity.com/paper/2104.10609/) (2021)
- [Dual networks based 3D Multi-Person Pose Estimation from Monocular Video](https://mlsanity.com/paper/2205.00748/) (2022)
- [Towards Single Camera Human 3D-Kinematics](https://mlsanity.com/paper/2301.05435/) (2023)
- [OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation](https://mlsanity.com/paper/2103.10180/) (2021)
- [Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification](https://mlsanity.com/paper/2210.14799/) (2022)
- [Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos](https://mlsanity.com/paper/2211.15868/) (2022)
- [BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations](https://mlsanity.com/paper/2112.10716/) (2021)
- [Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networks](https://mlsanity.com/paper/2106.14739/) (2021)
- [A Review on Human Pose Estimation](https://mlsanity.com/paper/2110.06877/) (2021)
- [Learning from the Pros: Extracting Professional Goalkeeper Technique from Broadcast Footage](https://mlsanity.com/paper/2202.12259/) (2022)
- [Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB](https://mlsanity.com/paper/2409.11104/) (2024)
- [PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation](https://mlsanity.com/paper/2107.03000/) (2021)
- [Instance-specific 6-DoF Object Pose Estimation from Minimal Annotations](https://mlsanity.com/paper/2207.13264/) (2022)
- [Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/2303.14888/) (2023)
- [Noise-in, Bias-out: Balanced and Real-time MoCap Solving](https://mlsanity.com/paper/2309.14330/) (2023)

## Abstract (arXiv)

Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem. The two-dimensional nature of the input results in intrinsic ambiguities which make inferring depth particularly difficult. Recently, researchers have demonstrated that the flexible statistical modelling capabilities of deep neural networks are sufficient to make such inferences with reasonable accuracy. However, many of these models use coordinate output techniques which are memory-intensive, not differentiable, and/or do not spatially generalise well. We propose improvements to 3D coordinate prediction which avoid the aforementioned undesirable traits by predicting 2D marginal heatmaps under an augmented soft-argmax scheme. Our resulting model, MargiPose, produces visually coherent heatmaps whilst maintaining differentiability. We are also able to achieve state-of-the-art accuracy on publicly available 3D human pose estimation data.