# 3D Human Pose Machines with Self-supervised Learning

arXiv: https://arxiv.org/abs/1901.03798 · HTML: https://mlsanity.com/paper/1901.03798/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2019.

## Built on by (most cited first, 17 of 17)

- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Recent Advances in Imitation Learning from Observation](https://mlsanity.com/paper/1905.13566/) (2019)
- [SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding](https://mlsanity.com/paper/2305.04868/) (2023)
- [EventHPE: Event-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2108.06819/) (2021)
- [DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders](https://mlsanity.com/paper/2108.08557/) (2021)
- [Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks](https://mlsanity.com/paper/2107.05825/) (2021)
- [Human Pose and Shape Estimation from Single Polarization Images](https://mlsanity.com/paper/2108.06834/) (2021)
- [Deep learning for 3D human pose estimation and mesh recovery: A survey](https://mlsanity.com/paper/2402.18844/) (2024)
- [Physics perception in sloshing scenes with guaranteed thermodynamic consistency](https://mlsanity.com/paper/2106.13301/) (2021)
- [Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer](https://mlsanity.com/paper/2303.09681/) (2023)
- [Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition](https://mlsanity.com/paper/2109.09166/) (2021)
- [BodyMAP -- Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed](https://mlsanity.com/paper/2404.03183/) (2024)
- [3D Human Scan With A Moving Event Camera](https://mlsanity.com/paper/2404.08504/) (2024)
- [Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2505.20611/) (2025)
- [Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction](https://mlsanity.com/paper/2510.26196/) (2025)
- [Capsules as viewpoint learners for human pose estimation](https://mlsanity.com/paper/2302.06194/) (2023)
- [Intelligent Image Sensing for Crime Analysis: A ML Approach towards Enhanced Violence Detection and Investigation](https://mlsanity.com/paper/2506.13910/) (2025)

## Abstract (arXiv)

Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests. In fact, completing this task is quite challenging due to the diverse appearances, viewpoints, occlusions and inherently geometric ambiguities inside monocular images. Most of the existing methods focus on designing some elaborate priors /constraints to directly regress 3D human poses based on the corresponding 2D human pose-aware features or 2D pose predictions. However, due to the insufficient 3D pose data for training and the domain gap between 2D space and 3D space, these methods have limited scalabilities for all practical scenarios (e.g., outdoor scene). Attempt to address this issue, this paper proposes a simple yet effective self-supervised correction mechanism to learn all intrinsic structures of human poses from abundant images. Specifically, the proposed mechanism involves two dual learning tasks, i.e., the 2D-to-3D pose transformation and 3D-to-2D pose projection, to serve as a bridge between 3D and 2D human poses in a type of "free" self-supervision for accurate 3D human pose estimation. The 2D-to-3D pose implies to sequentially regress intermediate 3D poses by transforming the pose representation from the 2D domain to the 3D domain under the sequence-dependent temporal context, while the 3D-to-2D pose projection contributes to refining the intermediate 3D poses by maintaining geometric consistency between the 2D projections of 3D poses and the estimated 2D poses. We further apply our self-supervised correction mechanism to develop a 3D human pose machine, which jointly integrates the 2D spatial relationship, temporal smoothness of predictions and 3D geometric knowledge. Extensive evaluations demonstrate the superior performance and efficiency of our framework over all the compared competing methods.