# Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning

arXiv: https://arxiv.org/abs/2311.02815 · HTML: https://mlsanity.com/paper/2311.02815/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 30 of 33)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Self-supervised 6D Object Pose Estimation for Robot Manipulation](https://mlsanity.com/paper/1909.10159/) (2019)
- [Self-Supervised Learning of 3D Human Pose using Multi-view Geometry](https://mlsanity.com/paper/1903.02330/) (2019)
- [Learning Detailed Face Reconstruction from a Single Image](https://mlsanity.com/paper/1611.05053/) (2016)
- [CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild](https://mlsanity.com/paper/2011.14679/) (2020)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis](https://mlsanity.com/paper/2004.04400/) (2020)
- [Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose](https://mlsanity.com/paper/1811.12004/) (2018)
- [Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving](https://mlsanity.com/paper/2112.12141/) (2021)
- [Learning to Generate Images with Perceptual Similarity Metrics](https://mlsanity.com/paper/1511.06409/) (2015)
- [Context Modeling in 3D Human Pose Estimation: A Unified Perspective](https://mlsanity.com/paper/2103.15507/) (2021)
- [Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers](https://mlsanity.com/paper/2210.06110/) (2022)
- [HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar](https://mlsanity.com/paper/2210.12564/) (2022)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving](https://mlsanity.com/paper/2212.07729/) (2022)
- [Self-supervised Learning for Precise Pick-and-place without Object Model](https://mlsanity.com/paper/2006.08373/) (2020)
- [A Study of the Generalizability of Self-Supervised Representations](https://mlsanity.com/paper/2109.09150/) (2021)
- [Neural Groundplans: Persistent Neural Scene Representations from a Single Image](https://mlsanity.com/paper/2207.11232/) (2022)
- [Simple and Lightweight Human Pose Estimation](https://mlsanity.com/paper/1911.10346/) (2019)
- [Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry](https://mlsanity.com/paper/2108.07777/) (2021)
- [Attention! A Lightweight 2D Hand Pose Estimation Approach](https://mlsanity.com/paper/2001.08047/) (2020)
- [Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment](https://mlsanity.com/paper/2301.06648/) (2023)
- [Self-supervised 3D Human Pose Estimation from a Single Image](https://mlsanity.com/paper/2304.02349/) (2023)
- [Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving](https://mlsanity.com/paper/2307.14889/) (2023)

## Built on by (most cited first, 1 of 1)

- [Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation](https://mlsanity.com/paper/2410.03858/) (2024)

## Abstract (arXiv)

The goal of 2D human pose estimation (HPE) is to localize anatomical landmarks, given an image of a person in a pose. SOTA techniques make use of thousands of labeled figures (finetuning transformers or training deep CNNs), acquired using labor-intensive crowdsourcing. On the other hand, self-supervised methods re-frame the HPE task as a reconstruction problem, enabling them to leverage the vast amount of unlabeled visual data, though at the present cost of accuracy. In this work, we explore ways to improve self-supervised HPE. We (1) analyze the relationship between reconstruction quality and pose estimation accuracy, (2) develop a model pipeline that outperforms the baseline which inspired our work, using less than one-third the amount of training data, and (3) offer a new metric suitable for self-supervised settings that measures the consistency of predicted body part length proportions. We show that a combination of well-engineered reconstruction losses and inductive priors can help coordinate pose learning alongside reconstruction in a self-supervised paradigm.