多边形网格
计算机科学
姿势
图形
邻接矩阵
人工智能
邻接表
顶点(图论)
卷积神经网络
模式识别(心理学)
计算机视觉
算法
理论计算机科学
计算机图形学(图像)
作者
Junxing Hu,Hongwen Zhang,Liang Wang,Min Ren,Zhenan Sun
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology
[Institute of Electrical and Electronics Engineers]
日期:2023-08-31
卷期号:34 (4): 2399-2413
被引量:1
标识
DOI:10.1109/tcsvt.2023.3310525
摘要
3D human pose and shape estimation from a single RGB image is an appealing yet challenging task. Due to the graph-like nature of human parametric models, a growing number of graph neural network-based approaches have been proposed and achieved promising results. However, existing methods build graphs for different instances based on the same template SMPL mesh, neglecting the geometric perception of individual properties. In this work, we propose an end-to-end method named Personalized Graph Generation (PGG) to construct the geometry-aware graph from an intermediate predicted human mesh. Specifically, a convolutional module initially regresses a coarse SMPL mesh tailored for each sample. Guided by the 3D structure of this personalized mesh, PGG extracts the local features from the 2D feature map. Then, these geometry-aware features are integrated with the specific coarse SMPL parameters as vertex features. Furthermore, a body-oriented adjacency matrix is adaptively generated according to the coarse mesh. It considers individual full-body relations between vertices, enhancing the perception of body geometry. Finally, a graph attentional module is utilized to predict the residuals to get the final results. Quantitative experiments across four benchmarks and qualitative comparisons on more datasets show that the proposed method outperforms state-of-the-art approaches for 3D human pose and shape estimation.
科研通智能强力驱动
Strongly Powered by AbleSci AI