HTNet: Human Topology Aware Network for 3D Human Pose Estimation

02/20/2023
by   Jialun Cai, et al.
0

3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological constraints for end joints at the part level. Further considering the hierarchy of the human topology, joint-level and body-level dependencies are captured via graph convolutional networks and self-attentions, respectively. Based on these designs, we propose a novel Human Topology aware Network (HTNet), which adopts a channel-split progressive strategy to sequentially learn the structural priors of the human topology from multiple semantic levels: joint, part, and body. Extensive experiments show that the proposed method improves the estimation accuracy by 18.7 state-of-the-art results on Human3.6M and MPI-INF-3DHP datasets. Code is available at https://github.com/vefalun/HTNet.

READ FULL TEXT
research
04/27/2023

Interweaved Graph and Attention Network for 3D Human Pose Estimation

Despite substantial progress in 3D human pose estimation from a single-v...
research
06/16/2023

EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors

Transformer is popular in recent 3D human pose estimation, which utilize...
research
02/17/2023

3D Human Pose Lifting with Grid Convolution

Existing lifting networks for regressing 3D human poses from 2D single-v...
research
11/23/2021

Hierarchical Graph Networks for 3D Human Pose Estimation

Recent 2D-to-3D human pose estimation works tend to utilize the graph st...
research
08/10/2023

Double-chain Constraints for 3D Human Pose Estimation in Images and Videos

Reconstructing 3D poses from 2D poses lacking depth information is parti...
research
02/22/2020

Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation

We propose a new deep learning network that introduces a deeper CNN chan...
research
07/12/2020

Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation

Recently, the leading performance of human pose estimation is dominated ...

Please sign up or login with your details

Forgot password? Click here to reset