# Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation

arXiv: https://arxiv.org/abs/2008.01388 · HTML: https://mlsanity.com/paper/2008.01388/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimation](https://mlsanity.com/paper/2109.10471/) (2021)
- [Leveraging MoCap Data for Human Mesh Recovery](https://mlsanity.com/paper/2110.09243/) (2021)
- [Crowd3D: Towards Hundreds of People Reconstruction from a Single Image](https://mlsanity.com/paper/2301.09376/) (2023)
- [Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition](https://mlsanity.com/paper/2109.09166/) (2021)
- [Semi-Supervised Visual Representation Learning for Fashion Compatibility](https://mlsanity.com/paper/2109.08052/) (2021)
- [Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation](https://mlsanity.com/paper/2204.01971/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimation](https://mlsanity.com/paper/2312.06409/) (2023)
- [Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization](https://mlsanity.com/paper/2205.02670/) (2022)

## Abstract (arXiv)

We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with their corresponding 3D pose representation. This is realized by learning a generative pose embedding which not only ensures plausible 3D pose predictions, but also eliminates the usual keypoint grouping operation as employed in prior bottom-up approaches. Further, we propose a practical deployment paradigm where paired 2D or 3D pose annotations are unavailable. In the absence of any paired supervision, we leverage a frozen network, as a teacher model, which is trained on an auxiliary task of multi-person 2D pose estimation. We cast the learning as a cross-modal alignment problem and propose training objectives to realize a shared latent space between two diverse modalities. We aim to enhance the model's ability to perform beyond the limiting teacher network by enriching the latent-to-3D pose mapping using artificially synthesized multi-person 3D scene samples. Our approach not only generalizes to in-the-wild images, but also yields a superior trade-off between speed and performance, compared to prior top-down approaches. Our approach also yields state-of-the-art multi-person 3D pose estimation performance among the bottom-up approaches under consistent supervision levels.