# A Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior

arXiv: https://arxiv.org/abs/2308.03411 · HTML: https://mlsanity.com/paper/2308.03411/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"](https://mlsanity.com/paper/1908.07201/) (2019)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [Creatures great and SMAL: Recovering the shape and motion of animals from video](https://mlsanity.com/paper/1811.05804/) (2018)
- [Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop](https://mlsanity.com/paper/2007.11110/) (2020)
- [Sim2real transfer learning for 3D human pose estimation: motion to the rescue](https://mlsanity.com/paper/1907.02499/) (2019)
- [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019)
- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [Pretraining boosts out-of-domain robustness for pose estimation](https://mlsanity.com/paper/1909.11229/) (2019)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)
- [AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild](https://mlsanity.com/paper/2103.13282/) (2021)
- [T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information](https://mlsanity.com/paper/2104.08029/) (2021)
- [Self-supervised 3D Human Pose Estimation from a Single Image](https://mlsanity.com/paper/2304.02349/) (2023)
- [Multiview Supervision By Registration](https://mlsanity.com/paper/1811.11251/) (2018)
- [Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video](https://mlsanity.com/paper/1511.09319/) (2015)
- [Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior](https://mlsanity.com/paper/2307.13361/) (2023)

## Built on by (most cited first, 2 of 2)

- [DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery](https://mlsanity.com/paper/2510.24117/) (2025)
- [Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis](https://mlsanity.com/paper/2410.09312/) (2024)

## Abstract (arXiv)

Obtaining labelled data to train deep learning methods for estimating animal pose is challenging. Recently, synthetic data has been widely used for pose estimation tasks, but most methods still rely on supervised learning paradigms utilising synthetic images and labels. Can training be fully unsupervised? Is a tiny synthetic dataset sufficient? What are the minimum assumptions that we could make for estimating animal pose? Our proposal addresses these questions through a simple yet effective self-supervised method that only assumes the availability of unlabelled images and a small set of synthetic 2D poses. We completely remove the need for any 3D or 2D pose annotations (or complex 3D animal models), and surprisingly our approach can still learn accurate 3D and 2D poses simultaneously. We train our method with unlabelled images of horses mainly collected for YouTube videos and a prior consisting of 2D synthetic poses. The latter is three times smaller than the number of images needed for training. We test our method on a challenging set of horse images and evaluate the predicted 3D and 2D poses. We demonstrate that it is possible to learn accurate animal poses even with as few assumptions as unlabelled images and a small set of 2D poses generated from synthetic data. Given the minimum requirements and the abundance of unlabelled data, our method could be easily deployed to different animals.