paper-with-me

Papers

Absolute Human Pose Estimation with Depth Prediction Network

2019-04-11 · Márton Véges, András Lőrincz

The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.

📄 PDF Abstract BibTeX arXiv:1904.05947

Code (1)

vegesm/depthpose 공식 구현 pytorch

Tasks

3D Human Pose EstimationDepth EstimationDepth PredictionPose EstimationPredictionTranslation

Similar Papers 제목 키워드 기반

Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates

2019-11-21 · Diogo C. Luvizon, Hedi Tabia, David Picard

3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective co…

3D Human Pose EstimationDepth EstimationDepth PredictionPose Estimation

HPERL: 3D Human Pose Estimation from RGB and LiDAR

2020-10-16 · Michael Fürst, Shriya T. P. Gupta, René Schuster, Oliver Wasenmüller 외

In-the-wild human pose estimation has a huge potential for various fields, ranging from animation and action recognition to intention recognition and prediction for autonomous driving. The current state-of-the-art is foc…

3D Human Pose EstimationAction RecognitionAutonomous DrivingIntent Detection+1

Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation

2022-01-01 · CVPR 2022 1 · Lei Jin, Chenyang Xu, Xiaojuan Wang, Yabo Xiao 외

The existing multi-person absolute 3D pose estimation methods are mainly based on two-stage paradigm, i.e., top-down or bottom-up, leading to redundant pipelines with high computation cost. We argue that it is more d…

3D Pose EstimationDepth EstimationPose Estimationregression

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

2020-07-17 · ECCV 2020 8 · Jiahao Lin, Gim Hee Lee

Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose. In this paper, we propose the Human Dep…

3D Multi-Person Pose Estimation (absolute)3D Multi-Person Pose Estimation (root-relative)3D Pose EstimationDepth Estimation+3

Absolute distance prediction based on deep learning object detection and monocular depth estimation models

2021-11-02 · Armin Masoumian, David G. F. Marei, Saddam Abdulwahab, Julian Cristiano 외

Determining the distance between the objects in a scene and the camera sensor from 2D images is feasible by estimating depth images using stereo cameras or 3D cameras. The outcome of depth estimation is relative distance…

Depth EstimationMonocular Depth Estimationobject-detectionObject Detection