# DirectPose: Direct End-to-End Multi-Person Pose Estimation

arXiv: https://arxiv.org/abs/1911.07451 · HTML: https://mlsanity.com/paper/1911.07451/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2019.

## Built on by (most cited first, 30 of 49)

- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Pose Recognition with Cascade Transformers](https://mlsanity.com/paper/2104.06976/) (2021)
- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation](https://mlsanity.com/paper/2302.01593/) (2023)
- [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)
- [FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions](https://mlsanity.com/paper/2105.14185/) (2021)
- [RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation](https://mlsanity.com/paper/2312.07526/) (2023)
- [Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation](https://mlsanity.com/paper/2308.07313/) (2023)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation](https://mlsanity.com/paper/2109.03622/) (2021)
- [InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation](https://mlsanity.com/paper/2107.08982/) (2021)
- [QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query](https://mlsanity.com/paper/2212.07855/) (2022)
- [Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks](https://mlsanity.com/paper/2209.13948/) (2022)
- [DistilPose: Tokenized Pose Regression with Heatmap Distillation](https://mlsanity.com/paper/2303.02455/) (2023)
- [Dynamic Graph Reasoning for Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2207.11341/) (2022)
- [You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception](https://mlsanity.com/paper/2312.05525/) (2023)
- [Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room](https://mlsanity.com/paper/2108.11801/) (2021)
- [Lightweight Super-Resolution Head for Human Pose Estimation](https://mlsanity.com/paper/2307.16765/) (2023)
- [Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions](https://mlsanity.com/paper/2407.15451/) (2024)
- [Object Detection Made Simpler by Eliminating Heuristic NMS](https://mlsanity.com/paper/2101.11782/) (2021)
- [AdaptivePose: Human Parts as Adaptive Points](https://mlsanity.com/paper/2112.13635/) (2021)
- [Learning Quality-aware Representation for Multi-person Pose Regression](https://mlsanity.com/paper/2201.01087/) (2022)
- [AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression](https://mlsanity.com/paper/2210.04014/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Referring Human Pose and Mask Estimation in the Wild](https://mlsanity.com/paper/2410.20508/) (2024)

## Abstract (arXiv)

We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose. Inspired by recent anchor-free object detectors, which directly regress the two corners of target bounding-boxes, the proposed framework directly predicts instance-aware keypoints for all the instances from a raw input image, eliminating the need for heuristic grouping in bottom-up methods or bounding-box detection and RoI operations in top-down ones. We also propose a novel Keypoint Alignment (KPAlign) mechanism, which overcomes the main difficulty: lack of the alignment between the convolutional features and predictions in this end-to-end framework. KPAlign improves the framework's performance by a large margin while still keeping the framework end-to-end trainable. With the only postprocessing non-maximum suppression (NMS), our proposed framework can detect multi-person keypoints with or without bounding-boxes in a single shot. Experiments demonstrate that the end-to-end paradigm can achieve competitive or better performance than previous strong baselines, in both bottom-up and top-down methods. We hope that our end-to-end approach can provide a new perspective for the human pose estimation task.