# Rethinking on Multi-Stage Networks for Human Pose Estimation

arXiv: https://arxiv.org/abs/1901.00148 · HTML: https://mlsanity.com/paper/1901.00148/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jan 2019.

## Built on by (most cited first, 30 of 58)

- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Poseur: Direct Human Pose Regression with Transformers](https://mlsanity.com/paper/2201.07412/) (2022)
- [TFPose: Direct Human Pose Estimation with Transformers](https://mlsanity.com/paper/2103.15320/) (2021)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [Regressive Domain Adaptation for Unsupervised Keypoint Detection](https://mlsanity.com/paper/2103.06175/) (2021)
- [Supervision by Registration and Triangulation for Landmark Detection](https://mlsanity.com/paper/2101.09866/) (2021)
- [MEGANE: Morphable Eyeglass and Avatar Network](https://mlsanity.com/paper/2302.04868/) (2023)
- [RelightableHands: Efficient Neural Relighting of Articulated Hand Models](https://mlsanity.com/paper/2302.04866/) (2023)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [URHand: Universal Relightable Hands](https://mlsanity.com/paper/2401.05334/) (2024)
- [ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild](https://mlsanity.com/paper/2205.05177/) (2022)
- [Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation](https://mlsanity.com/paper/2208.00090/) (2022)
- [Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module](https://mlsanity.com/paper/2303.04346/) (2023)
- [Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding](https://mlsanity.com/paper/2303.15417/) (2023)
- [Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2203.07697/) (2022)
- [Heatmap Distribution Matching for Human Pose Estimation](https://mlsanity.com/paper/2210.00740/) (2022)
- [Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling for Pitch Analysis](https://mlsanity.com/paper/2309.01010/) (2023)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [Lightweight Super-Resolution Head for Human Pose Estimation](https://mlsanity.com/paper/2307.16765/) (2023)
- [OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation](https://mlsanity.com/paper/2103.10180/) (2021)
- [NIMBLE: A Non-rigid Hand Model with Bones and Muscles](https://mlsanity.com/paper/2202.04533/) (2022)
- [Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras](https://mlsanity.com/paper/2401.15616/) (2024)
- [SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation](https://mlsanity.com/paper/2104.02486/) (2021)
- [Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation](https://mlsanity.com/paper/2207.02425/) (2022)

## Abstract (arXiv)

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.