# Stacked Hourglass Networks for Human Pose Estimation

arXiv: https://arxiv.org/abs/1603.06937 · HTML: https://mlsanity.com/paper/1603.06937/

## Key facts

- Cited by 915 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2016.

## Built on by (most cited first, 30 of 915)

- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [Sequential Modeling Enables Scalable Learning for Large Vision Models](https://mlsanity.com/paper/2312.00785/) (2023)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time](https://mlsanity.com/paper/2106.05266/) (2021)
- [PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark](https://mlsanity.com/paper/2203.11089/) (2022)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [MPViT: Multi-Path Vision Transformer for Dense Prediction](https://mlsanity.com/paper/2112.11010/) (2021)

## Abstract (arXiv)

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.