Papers › Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation
Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation
Qun Li, Ziyi Zhang, Fu Xiao, Feng Zhang, Bir Bhanu
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these problems, we present a Dynamic lightweight High-Resolution Network (Dite-HRNet), which can efficiently extract multi-scale contextual information and model long-range spatial dependency for human pose estimation. Specifically, we propose two methods, dynamic split convolution and adaptive context modeling, and embed them into two novel lightweight blocks, which are named dynamic multi-scale context block and dynamic global context block. These two blocks, as the basic component units of our Dite-HRNet, are specially designed for the high-resolution networks to make full use of the parallel multi-resolution architecture. Experimental results show that the proposed network achieves superior performance on both COCO and MPII human pose estimation datasets, surpassing the state-of-the-art lightweight networks. Code is available at: https://github.com/ZiyiZhang27/Dite-HRNet.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Pose Estimation | COCO test-dev | Dite-HRNet-30 | AP | 70.6 | #31 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | Dite-HRNet-30 | AP50 | 90.8 | #31 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | Dite-HRNet-30 | AP75 | 78.2 | #31 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | Dite-HRNet-30 | APL | 76.1 | #31 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | Dite-HRNet-30 | APM | 67.4 | #31 of 47 | Archive leaderboard | report |
| Pose Estimation | COCO test-dev | Dite-HRNet-30 | AR | 76.4 | #31 of 47 | Archive leaderboard | report |
| Pose Estimation | MPII Human Pose | Dite-HRNet-30 | PCKh-0.5 | 87.6 | #34 of 46 | 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
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