# MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation

arXiv: https://arxiv.org/abs/2003.13239 · HTML: https://mlsanity.com/paper/2003.13239/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo](https://mlsanity.com/paper/2104.02273/) (2021)
- [TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.09554/) (2021)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling](https://mlsanity.com/paper/2208.10211/) (2022)
- [MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision](https://mlsanity.com/paper/2108.04869/) (2021)
- [AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2201.08093/) (2022)
- [Estimation of 3D Human Pose Using Prior Knowledge](https://mlsanity.com/paper/2105.03807/) (2021)
- [Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstruction](https://mlsanity.com/paper/2312.17106/) (2023)
- [Semi-supervised Dense Keypoints Using Unlabeled Multiview Images](https://mlsanity.com/paper/2109.09299/) (2021)

## Abstract (arXiv)

Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts (1) a generic fusion model shared by all cameras, and (2) lightweight camera-dependent transformations. Furthermore, the generic model is learned from many cameras by a meta-learning style algorithm to maximize its adaptation capability to various camera poses. We observe in experiments that MetaFuse finetuned on the public datasets outperforms the state-of-the-arts by a large margin which validates its value in practice.