# VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data arXiv: https://arxiv.org/abs/2207.09949 ยท HTML: https://mlsanity.com/paper/2207.09949/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 37 of its 50 references that are in the map. - First posted on arXiv 20 Jul 2022. ## Builds on (most cited first, 30 of 37) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019) - [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016) - [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) - [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017) - [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016) - [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (2017) - [Long-term Human Motion Prediction with Scene Context](https://mlsanity.com/paper/2007.03672/) (2020) - [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019) - [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1907.11346/) (2019) - [Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach](https://mlsanity.com/paper/1704.02447/) (2017) - [LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images](https://mlsanity.com/paper/1803.00455/) (2018) - [3D Human Pose Estimation in the Wild by Adversarial Learning](https://mlsanity.com/paper/1803.09722/) (2018) - [RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1902.09868/) (2019) - [Cascaded deep monocular 3D human pose estimation with evolutionary training data](https://mlsanity.com/paper/2006.07778/) (2020) - [3D Human Pose Estimation from a Single Image via Distance Matrix Regression](https://mlsanity.com/paper/1611.09010/) (2016) - [SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation](https://mlsanity.com/paper/2008.11469/) (2020) - [HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2008.00206/) (2020) - [AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild](https://mlsanity.com/paper/2010.13302/) (2020) - [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021) - [Context Modeling in 3D Human Pose Estimation: A Unified Perspective](https://mlsanity.com/paper/2103.15507/) (2021) - [Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2004.00329/) (2020) - [MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation](https://mlsanity.com/paper/2007.07227/) (2020) - [Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach](https://mlsanity.com/paper/2003.11163/) (2020) - [Reconstructing NBA Players](https://mlsanity.com/paper/2007.13303/) (2020) - [Robust Estimation of 3D Human Poses from a Single Image](https://mlsanity.com/paper/1406.2282/) (2014) - [Deep Multitask Architecture for Integrated 2D and 3D Human Sensing](https://mlsanity.com/paper/1701.08985/) (2017) ## Built on by (most cited first, 10 of 10) - [3D Human Mesh Estimation from Virtual Markers](https://mlsanity.com/paper/2303.11726/) (2023) - [PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation](https://mlsanity.com/paper/2211.11734/) (2022) - [Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild](https://mlsanity.com/paper/2309.08644/) (2023) - [Progressive Multi-view Human Mesh Recovery with Self-Supervision](https://mlsanity.com/paper/2212.05223/) (2022) - [ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning](https://mlsanity.com/paper/2307.01200/) (2023) - [Reconstructing Close Human Interactions from Multiple Views](https://mlsanity.com/paper/2401.16173/) (2024) - [Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery](https://mlsanity.com/paper/2411.16289/) (2024) - [Exploring the Impact of Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15203/) (2024) - [MuPPet: Multi-person 2D-to-3D Pose Lifting](https://mlsanity.com/paper/2604.09715/) (2026) - [Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images](https://mlsanity.com/paper/2506.19747/) (2025) ## Abstract (arXiv) While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of the existing methods and find that they get notably larger errors when tested on different cameras, human poses and appearance. To address the problem, we introduce VirtualPose, a two-stage learning framework to exploit the hidden "free lunch" specific to this task, i.e. generating infinite number of poses and cameras for training models at no cost. To that end, the first stage transforms images to abstract geometry representations (AGR), and then the second maps them to 3D poses. It addresses the generalization issue from two aspects: (1) the first stage can be trained on diverse 2D datasets to reduce the risk of over-fitting to limited appearance; (2) the second stage can be trained on diverse AGR synthesized from a large number of virtual cameras and poses. It outperforms the SOTA methods without using any paired images and 3D poses from the benchmarks, which paves the way for practical applications. Code is available at https://github.com/wkom/VirtualPose.