mlsanityData to 14 Oct 2026

Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate Model for Real-time Edge Computing

arXiv 2111.04226 ↗First posted 8 Nov 2021cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

In this study, we present a pragmatic lightweight pose estimation model. Our model can achieve real-time predictions using low-power embedded devices. This system was found to be very accurate and achieved a 94.5% accuracy of SOTA HRNet 256x192 using a computational cost of only 3.8% on COCO test dataset. Our model adopts an encoder-decoder architecture and is carefully downsized to improve its efficiency. We especially focused on optimizing the deconvolution layers and observed that the channel reduction of the deconvolution layers contributes significantly to reducing computational resource consumption without degrading the accuracy of this system. We also incorporated recent model agnostic techniques such as DarkPose and distillation training to maximize the efficiency of our model. Furthermore, we applied model quantization to exploit multi/mixed precision features. Our FP16'ed model (COCO AP 70.0) operates at ~60-fps on NVIDIA Jetson AGX Xavier and ~200 fps on NVIDIA Quadro RTX6000.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 17 references that are in the map. First posted on arXiv 8 Nov 2021.

Builds on

14 of 17 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  8. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  9. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  10. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  11. 2020BlazePose: On-device Real-time Body Pose trackingcited by 113
  12. 2018Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPosecited by 42
2 more
  1. 2019Simple and Lightweight Human Pose Estimationcited by 10
  2. 2020EfficientPose: Efficient Human Pose Estimation with Neural Architecture Searchcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Full-Resolution Encoder-Decoder Networks with Multi-Scale Feature Fusion for Human Pose Estimation
  2. 2023BiHRNet: A Binary high-resolution network for Human Pose Estimation
  3. 2022FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices
  4. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
  5. 2025SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop
  7. 2025QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
  8. 2022HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation