Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization

by   Yu Zhan, et al.

In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this challenge, we convert the input from pixel space to 3D normalized rays. This conversion makes our approach robust to camera intrinsic parameter changes. To deal with the in-the-wild camera extrinsic parameter variations, Ray3D explicitly takes the camera extrinsic parameters as an input and jointly models the distribution between the 3D pose rays and camera extrinsic parameters. This novel network design is the key to the outstanding generalizability of Ray3D approach. To have a comprehensive understanding of how the camera intrinsic and extrinsic parameter variations affect the accuracy of absolute 3D key-point localization, we conduct in-depth systematic experiments on three single person 3D benchmarks as well as one synthetic benchmark. These experiments demonstrate that our method significantly outperforms existing state-of-the-art models. Our code and the synthetic dataset are available at https://github.com/YxZhxn/Ray3D .


page 13

page 16

page 17

page 18

page 19


Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

Although significant improvement has been achieved in 3D human pose esti...

Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration

The filming of sporting events projects and flattens the movement of ath...

HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

Current works on multi-person 3D pose estimation mainly focus on the est...

Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

Monocular 3D Human Pose Estimation from static images is a challenging p...

AI-supported Framework of Semi-Automatic Monoplotting for Monocular Oblique Visual Data Analysis

In the last decades, the development of smartphones, drones, aerial patr...

DIME-Net: Neural Network-Based Dynamic Intrinsic Parameter Rectification for Cameras with Optical Image Stabilization System

Optical Image Stabilization (OIS) system in mobile devices reduces image...

Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR

Depth estimation is usually ill-posed and ambiguous for monocular camera...

Please sign up or login with your details

Forgot password? Click here to reset