mlsanityData to 7 Oct 2026

MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices

arXiv 2308.09084 ↗First posted 17 Aug 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present MovePose, an optimized lightweight convolutional neural network designed specifically for real-time body pose estimation on CPU-based mobile devices. The current solutions do not provide satisfactory accuracy and speed for human posture estimation, and MovePose addresses this gap. It aims to maintain real-time performance while improving the accuracy of human posture estimation for mobile devices. Our MovePose algorithm has attained an Mean Average Precision (mAP) score of 68.0 on the COCO citecocodata validation dataset. The MovePose algorithm displayed efficiency with a performance of 69+ frames per second (fps) when run on an Intel i9-10920x CPU. Additionally, it showcased an increased performance of 452+ fps on an NVIDIA RTX3090 GPU. On an Android phone equipped with a Snapdragon 8 + 4G processor, the fps reached above 11. To enhance accuracy, we incorporated three techniques: deconvolution, large kernel convolution, and coordinate classification methods. Compared to basic upsampling, deconvolution is trainable, improves model capacity, and enhances the receptive field. Large kernel convolution strengthens these properties at a decreased computational cost. In summary, MovePose provides high accuracy and real-time performance, marking it a potential tool for a variety of applications, including those focused on mobile-side human posture estimation. The code and models for this algorithm will be made publicly accessible.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 29 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

26 of 29 references.

References · 26

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2019Objects as Pointscited by 1,172
  7. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  12. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
14 more
  1. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  2. 2016Convolutional Pose Machinescited by 325
  3. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  4. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  5. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  6. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  7. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  8. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  9. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  10. 2020BlazePose: On-device Real-time Body Pose trackingcited by 112
  11. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  12. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  13. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  14. 2023Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approachcited by 2

Built on by

Not cited yet.