Learnable human mesh triangulation for 3D human pose and shape estimation

by   Sungho Chun, et al.

Compared to joint position, the accuracy of joint rotation and shape estimation has received relatively little attention in the skinned multi-person linear model (SMPL)-based human mesh reconstruction from multi-view images. The work in this field is broadly classified into two categories. The first approach performs joint estimation and then produces SMPL parameters by fitting SMPL to resultant joints. The second approach regresses SMPL parameters directly from the input images through a convolutional neural network (CNN)-based model. However, these approaches suffer from the lack of information for resolving the ambiguity of joint rotation and shape reconstruction and the difficulty of network learning. To solve the aforementioned problems, we propose a two-stage method. The proposed method first estimates the coordinates of mesh vertices through a CNN-based model from input images, and acquires SMPL parameters by fitting the SMPL model to the estimated vertices. Estimated mesh vertices provide sufficient information for determining joint rotation and shape, and are easier to learn than SMPL parameters. According to experiments using Human3.6M and MPI-INF-3DHP datasets, the proposed method significantly outperforms the previous works in terms of joint rotation and shape estimation, and achieves competitive performance in terms of joint location estimation.


page 1

page 6

page 7

page 8

page 10

page 11

page 13

page 14


Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose

Most of the recent deep learning-based 3D human pose and mesh estimation...

Representation learning of vertex heatmaps for 3D human mesh reconstruction from multi-view images

This study addresses the problem of 3D human mesh reconstruction from mu...

Joint Hand Detection and Rotation Estimation by Using CNN

Hand detection is essential for many hand related tasks, e.g. parsing ha...

Convolutional Mesh Regression for Single-Image Human Shape Reconstruction

This paper addresses the problem of 3D human pose and shape estimation f...

Lightweight Estimation of Hand Mesh and Biomechanically Feasible Kinematic Parameters

3D hand pose estimation is a long-standing challenge in both robotics an...

Deep learning-based estimation of whole-body kinematics from multi-view images

It is necessary to analyze the whole-body kinematics (including joint lo...

Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view

From an image of a person, we can easily infer the natural 3D pose and s...

Please sign up or login with your details

Forgot password? Click here to reset