# Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/1903.08839 · HTML: https://mlsanity.com/paper/1903.08839/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2019.

## Built on by (most cited first, 23 of 23)

- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.14304/) (2021)
- [PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation](https://mlsanity.com/paper/2105.02465/) (2021)
- [Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision](https://mlsanity.com/paper/2201.07929/) (2022)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network](https://mlsanity.com/paper/2105.10882/) (2021)
- [MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks](https://mlsanity.com/paper/2112.10082/) (2021)
- [G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data](https://mlsanity.com/paper/2310.15422/) (2023)
- [FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction](https://mlsanity.com/paper/2105.01937/) (2021)
- [Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation](https://mlsanity.com/paper/2204.01971/) (2022)
- [Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge](https://mlsanity.com/paper/2211.11983/) (2022)
- [View Consistency Aware Holistic Triangulation for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.11301/) (2023)
- [Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos](https://mlsanity.com/paper/2106.14706/) (2021)
- [Unsupervised View-Invariant Human Posture Representation](https://mlsanity.com/paper/2109.08730/) (2021)
- [Disentangling Geometric Deformation Spaces in Generative Latent Shape Models](https://mlsanity.com/paper/2103.00142/) (2021)
- [TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video](https://mlsanity.com/paper/2105.06599/) (2021)
- [Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation](https://mlsanity.com/paper/2108.13258/) (2021)
- [Unsupervised 3D Keypoint Discovery with Multi-View Geometry](https://mlsanity.com/paper/2211.12829/) (2022)
- [DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain](https://mlsanity.com/paper/2406.03017/) (2024)
- [Semi-supervised Dense Keypoints Using Unlabeled Multiview Images](https://mlsanity.com/paper/2109.09299/) (2021)
- [Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection](https://mlsanity.com/paper/2601.12919/) (2026)
- [RSB-Pose: Robust Short-Baseline Binocular 3D Human Pose Estimation with Occlusion Handling](https://mlsanity.com/paper/2311.14242/) (2023)
- [UniPose: Unified Cross-modality Pose Prior Propagation towards RGB-D data for Weakly Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2509.23376/) (2025)

## Abstract (arXiv)

Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures. However, the generalizability to different environments remains an elusive goal. In this work, we propose a geometry-aware 3D representation for the human pose to address this limitation by using multiple views in a simple auto-encoder model at the training stage and only 2D keypoint information as supervision. A view synthesis framework is proposed to learn the shared 3D representation between viewpoints with synthesizing the human pose from one viewpoint to the other one. Instead of performing a direct transfer in the raw image-level, we propose a skeleton-based encoder-decoder mechanism to distil only pose-related representation in the latent space. A learning-based representation consistency constraint is further introduced to facilitate the robustness of latent 3D representation. Since the learnt representation encodes 3D geometry information, mapping it to 3D pose will be much easier than conventional frameworks that use an image or 2D coordinates as the input of 3D pose estimator. We demonstrate our approach on the task of 3D human pose estimation. Comprehensive experiments on three popular benchmarks show that our model can significantly improve the performance of state-of-the-art methods with simply injecting the representation as a robust 3D prior.