TRB: A Novel Triplet Representation for Understanding 2D Human Body

by   Haodong Duan, et al.

Human pose and shape are two important components of 2D human body. However, how to efficiently represent both of them in images is still an open question. In this paper, we propose the Triplet Representation for Body (TRB) – a compact 2D human body representation, with skeleton keypoints capturing human pose information and contour keypoints containing human shape information. TRB not only preserves the flexibility of skeleton keypoint representation, but also contains rich pose and human shape information. Therefore, it promises broader application areas, such as human shape editing and conditional image generation. We further introduce the challenging problem of TRB estimation, where joint learning of human pose and shape is required. We construct several large-scale TRB estimation datasets, based on popular 2D pose datasets: LSP, MPII, COCO. To effectively solve TRB estimation, we propose a two-branch network (TRB-net) with three novel techniques, namely X-structure (Xs), Directional Convolution (DC) and Pairwise Mapping (PM), to enforce multi-level message passing for joint feature learning. We evaluate our proposed TRB-net and several leading approaches on our proposed TRB datasets, and demonstrate the superiority of our method through extensive evaluations.


page 2

page 4

page 6

page 8


A novel joint points and silhouette-based method to estimate 3D human pose and shape

This paper presents a novel method for 3D human pose and shape estimatio...

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

Model-based 3D pose and shape estimation methods reconstruct a full 3D m...

Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling

We present a method for simultaneously estimating 3D human pose and body...

Human Pose and Shape Estimation from Single Polarization Images

This paper focuses on a new problem of estimating human pose and shape f...

DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare

We present DenseRaC, a novel end-to-end framework for jointly estimating...

Structured Feature Learning for Pose Estimation

In this paper, we propose a structured feature learning framework to rea...

SMPLR: Deep SMPL reverse for 3D human pose and shape recovery

A recent trend in 3D human pose and shape estimation is to use deep lear...

Please sign up or login with your details

Forgot password? Click here to reset