Full-Resolution Encoder-Decoder Networks with Multi-Scale Feature Fusion for Human Pose Estimation

06/01/2021
by   Jie Ou, et al.
0

To achieve more accurate 2D human pose estimation, we extend the successful encoder-decoder network, simple baseline network (SBN), in three ways. To reduce the quantization errors caused by the large output stride size, two more decoder modules are appended to the end of the simple baseline network to get full output resolution. Then, the global context blocks (GCBs) are added to the encoder and decoder modules to enhance them with global context features. Furthermore, we propose a novel spatial-attention-based multi-scale feature collection and distribution module (SA-MFCD) to fuse and distribute multi-scale features to boost the pose estimation. Experimental results on the MS COCO dataset indicate that our network can remarkably improve the accuracy of human pose estimation over SBN, our network using ResNet34 as the backbone network can even achieve the same accuracy as SBN with ResNet152, and our networks can achieve superior results with big backbone networks.

READ FULL TEXT
research
03/30/2021

Graph Stacked Hourglass Networks for 3D Human Pose Estimation

In this paper, we propose a novel graph convolutional network architectu...
research
08/26/2019

SPGNet: Semantic Prediction Guidance for Scene Parsing

Multi-scale context module and single-stage encoder-decoder structure ar...
research
09/22/2019

Pixel-Level Dense Prediction without Decoder

Pixel-level dense prediction tasks such as keypoint estimation are domin...
research
12/13/2020

Efficient Human Pose Estimation by Learning Deeply Aggregated Representations

In this paper, we propose an efficient human pose estimation network (DA...
research
11/08/2021

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

In this study, we present a pragmatic lightweight pose estimation model....
research
05/27/2020

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling

Existing CNN-based methods for pixel labeling heavily depend on multi-sc...
research
10/30/2020

PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift

Object pose estimation enables robots to understand and interact with th...

Please sign up or login with your details

Forgot password? Click here to reset