• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images


Abstract

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
B. Kim, Y. Choo, H. I. Jeong, C. Kim, S. Shin, J. Kim, "Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images," KSII Transactions on Internet and Information Systems, vol. 16, no. 7, pp. 2328-2344, 2022. DOI: 10.3837/tiis.2022.07.011.

[ACM Style]
Boeun Kim, YeonSeung Choo, Hea In Jeong, Chung-Il Kim, Saim Shin, and Jungho Kim. 2022. Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images. KSII Transactions on Internet and Information Systems, 16, 7, (2022), 2328-2344. DOI: 10.3837/tiis.2022.07.011.

[BibTeX Style]
@article{tiis:25844, title="Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images", author="Boeun Kim and YeonSeung Choo and Hea In Jeong and Chung-Il Kim and Saim Shin and Jungho Kim and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2022.07.011}, volume={16}, number={7}, year="2022", month={July}, pages={2328-2344}}