# Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2006.14107 · HTML: https://mlsanity.com/paper/2006.14107/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 26 of 26)

- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision](https://mlsanity.com/paper/2203.15625/) (2022)
- [Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation](https://mlsanity.com/paper/2307.03833/) (2023)
- [Self-supervised Human Mesh Recovery with Cross-Representation Alignment](https://mlsanity.com/paper/2209.04596/) (2022)
- [Markerless Multi-view 3D Human Pose Estimation: a survey](https://mlsanity.com/paper/2407.03817/) (2024)
- [Self-supervised 3D Human Pose Estimation from a Single Image](https://mlsanity.com/paper/2304.02349/) (2023)
- [HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2503.23331/) (2025)
- [Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2202.04287/) (2022)
- [Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling](https://mlsanity.com/paper/2308.10705/) (2023)
- [Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation](https://mlsanity.com/paper/2204.01971/) (2022)
- [Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views](https://mlsanity.com/paper/2403.02063/) (2024)
- [Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery](https://mlsanity.com/paper/2204.01276/) (2022)
- [Unsupervised 3D Keypoint Discovery with Multi-View Geometry](https://mlsanity.com/paper/2211.12829/) (2022)
- [Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation](https://mlsanity.com/paper/2312.07051/) (2023)
- [Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2405.17016/) (2024)
- [Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance](https://mlsanity.com/paper/2505.18342/) (2025)
- [EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors](https://mlsanity.com/paper/2306.09615/) (2023)
- ["Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation](https://mlsanity.com/paper/2205.05980/) (2022)
- [Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation](https://mlsanity.com/paper/2209.00618/) (2022)
- [Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes](https://mlsanity.com/paper/2402.02736/) (2024)
- [Self-learning Canonical Space for Multi-view 3D Human Pose Estimation](https://mlsanity.com/paper/2403.12440/) (2024)
- [X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation](https://mlsanity.com/paper/2411.13026/) (2024)
- [Toward Efficient Generalization in 3D Human Pose Estimation via a Canonical Domain Approach](https://mlsanity.com/paper/2501.16146/) (2025)
- [Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors](https://mlsanity.com/paper/2507.12336/) (2025)

## Abstract (arXiv)

Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale in-studio datasets remains questionable, as these models often perform unsatisfactorily on unseen in-the-wild environments. Though weakly-supervised models have been proposed to address this shortcoming, performance of such models relies on availability of paired supervision on some related tasks, such as 2D pose or multi-view image pairs. In contrast, we propose a novel kinematic-structure-preserved unsupervised 3D pose estimation framework, which is not restrained by any paired or unpaired weak supervisions. Our pose estimation framework relies on a minimal set of prior knowledge that defines the underlying kinematic 3D structure, such as skeletal joint connectivity information with bone-length ratios in a fixed canonical scale. The proposed model employs three consecutive differentiable transformations named as forward-kinematics, camera-projection and spatial-map transformation. This design not only acts as a suitable bottleneck stimulating effective pose disentanglement but also yields interpretable latent pose representations avoiding training of an explicit latent embedding to pose mapper. Furthermore, devoid of unstable adversarial setup, we re-utilize the decoder to formalize an energy-based loss, which enables us to learn from in-the-wild videos, beyond laboratory settings. Comprehensive experiments demonstrate our state-of-the-art unsupervised and weakly-supervised pose estimation performance on both Human3.6M and MPI-INF-3DHP datasets. Qualitative results on unseen environments further establish our superior generalization ability.