# Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation

arXiv: https://arxiv.org/abs/2010.06218 · HTML: https://mlsanity.com/paper/2010.06218/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2020.

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

- [To The Point: Correspondence-driven monocular 3D category reconstruction](https://mlsanity.com/paper/2106.05662/) (2021)
- [Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry](https://mlsanity.com/paper/2108.07777/) (2021)
- [Markerless Multi-view 3D Human Pose Estimation: a survey](https://mlsanity.com/paper/2407.03817/) (2024)
- [Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes](https://mlsanity.com/paper/2503.13739/) (2025)
- [Enhancing Egocentric 3D Pose Estimation with Third Person Views](https://mlsanity.com/paper/2201.02017/) (2022)
- [Spatiotemporal Multi-Camera Calibration using Freely Moving People](https://mlsanity.com/paper/2502.12546/) (2025)
- [End-to-End Learning of Multi-category 3D Pose and Shape Estimation](https://mlsanity.com/paper/2112.10196/) (2021)
- [Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images](https://mlsanity.com/paper/2211.07491/) (2022)
- [DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion](https://mlsanity.com/paper/2502.16419/) (2025)

## Abstract (arXiv)

Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit small annotated data sets by fine-tuning networks pre-trained via self-supervised learning on (large) unlabeled data sets. To drive such networks towards supporting 3D pose estimation during the pre-training step, we introduce a novel self-supervised feature learning task designed to focus on the 3D structure in an image. We exploit images extracted from videos captured with a multi-view camera system. The task is to classify whether two images depict two views of the same scene up to a rigid transformation. In a multi-view data set, where objects deform in a non-rigid manner, a rigid transformation occurs only between two views taken at the exact same time, i.e., when they are synchronized. We demonstrate the effectiveness of the synchronization task on the Human3.6M data set and achieve state-of-the-art results in 3D human pose estimation.