Papers › RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation

RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation

11 Jul 2024arXiv:2407.08634archive 2025-07-28

Tao Jiang, Xinchen Xie, Yining Li

Whole-body pose estimation is a challenging task that requires simultaneous prediction of keypoints for the body, hands, face, and feet. Whole-body pose estimation aims to predict fine-grained pose information for the human body, including the face, torso, hands, and feet, which plays an important role in the study of human-centric perception and generation and in various applications. In this work, we present RTMW (Real-Time Multi-person Whole-body pose estimation models), a series of high-performance models for 2D/3D whole-body pose estimation. We incorporate RTMPose model architecture with FPN and HEM (Hierarchical Encoding Module) to better capture pose information from different body parts with various scales. The model is trained with a rich collection of open-source human keypoint datasets with manually aligned annotations and further enhanced via a two-stage distillation strategy. RTMW demonstrates strong performance on multiple whole-body pose estimation benchmarks while maintaining high inference efficiency and deployment friendliness. We release three sizes: m/l/x, with RTMW-l achieving a 70.2 mAP on the COCO-Wholebody benchmark, making it the first open-source model to exceed 70 mAP on this benchmark. Meanwhile, we explored the performance of RTMW in the task of 3D whole-body pose estimation, conducting image-based monocular 3D whole-body pose estimation in a coordinate classification manner. We hope this work can benefit both academic research and industrial applications. The code and models have been made publicly available at: https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

open-mmlab/mmpose officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

2D Human Pose Estimation2D Pose Estimation3D Human Pose Estimation3D Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation COCO-WholeBody RTMW-x WB 70.2 #1 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-x body 76.3 #1 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-x face 88.4 #1 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-x foot 79.6 #1 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-x hand 66.4 #1 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-m WB 58 #10 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-m body 67.6 #10 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-m face 78.3 #10 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-m foot 67.1 #10 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody RTMW-m hand 49.1 #10 of 15 Archive leaderboard report
3D Human Pose Estimation H3WB RTMW3D-x MPJPE 57 #2 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionConvolutionFPN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections