Papers › EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

16 Jul 2020arXiv:2007.08090archive 2025-07-28

Christopher Neff, Aneri Sheth, Steven Furgurson, Hamed Tabkhi

There is an increasing demand for lightweight multi-person pose estimation for many emerging smart IoT applications. However, the existing algorithms tend to have large model sizes and intense computational requirements, making them ill-suited for real-time applications and deployment on resource-constrained hardware. Lightweight and real-time approaches are exceedingly rare and come at the cost of inferior accuracy. In this paper, we present EfficientHRNet, a family of lightweight multi-person human pose estimators that are able to perform in real-time on resource-constrained devices. By unifying recent advances in model scaling with high-resolution feature representations, EfficientHRNet creates highly accurate models while reducing computation enough to achieve real-time performance. The largest model is able to come within 4.4% accuracy of the current state-of-the-art, while having 1/3 the model size and 1/6 the computation, achieving 23 FPS on Nvidia Jetson Xavier. Compared to the top real-time approach, EfficientHRNet increases accuracy by 22% while achieving similar FPS with 1/3 the power. At every level, EfficientHRNet proves to be more computationally efficient than other bottom-up 2D human pose estimation approaches, while achieving highly competitive accuracy.

Paper PDF Code

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

Code

TeCSAR-UNCC/EfficientHRNet mentioned on GitHubpytorch report

code-implementation1/Code9 mindspore 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 Estimation Multi-Person Pose Estimation Pose Estimation Vocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution Average Pooling Batch Normalization Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Dropout EfficientNet HRNet Inverted Residual Block Pointwise Convolution RMSProp ReLU Residual Connection Sigmoid Activation Squeeze-and-Excitation Block

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