PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose

2019-10-26 · Ju Yong Chang, Gyeongsik Moon, Kyoung Mu Lee

This study presents a new network (i.e., PoseLifter) that can lift a 2D human pose to an absolute 3D pose in a camera coordinate system. The proposed network estimates the absolute 3D location of a target subject and generates an improved 3D relative pose estimation compared with existing pose-lifting methods. Using the PoseLifter with a 2D pose estimator in a cascade fashion can estimate a 3D human pose from a single RGB image. In this case, we empirically prove that using realistic 2D poses synthesized with the real error distribution of 2D body joints considerably improves the performance of our PoseLifter. The proposed method is applied to public datasets to achieve state-of-the-art 2D-to-3D pose lifting and 3D human pose estimation.

📄 PDF Abstract BibTeX arXiv:1910.12029

Code (1)

juyongchang/PoseLifter 공식 구현 pytorch

Tasks

3D Human Pose Estimation Pose Estimation

Multi-person 3D pose estimation from a single image captured by a fisheye camera

2022-07-09 · Computer Vision and Image Understanding 2022 7 · YaHui Zhang, ShaoDi You, Sezer Karaoglu, Theo Gevers

Multi-person 3D pose estimation with absolute depths for a fisheye camera is a challenging task but with valuable applications in daily life, especially for video surveillance. However, to the best of our knowledge, such…

3D Human Pose Estimation 3D Pose Estimation Pose Estimation

Mocap-2-to-3: Lifting 2D Diffusion-Based Pretrained Models for 3D Motion Capture

2025-03-05 · Zhumei Wang, Zechen Hu, Ruoxi Guo, Huaijin Pi 외

Recovering absolute poses in the world coordinate system from monocular views presents significant challenges. Two primary issues arise in this context. Firstly, existing methods rely on 3D motion data for training, whic…

Generating Labels for Regression of Subjective Constructs using Triplet Embeddings

2019-04-02 · Karel Mundnich, Brandon M. Booth, Benjamin Girault, Shrikanth Narayanan

Human annotations serve an important role in computational models where the target constructs under study are hidden, such as dimensions of affect. This is especially relevant in machine learning, where subjective labels…

regression Triplet

On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting

2026-01-20 · Pavlo Melnyk, Cuong Le, Urs Waldmann, Per-Erik Forssén 외 arxiv

Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3D human pose estimation (HPE), where the goal is to predict a 3D point s…

3D Human Pose Estimation Keypoint Detection Data Augmentation

PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space

2026-02-01 · Jinghong Zheng, Changlong Jiang, Yang Xiao, Jiaqi Li 외 arxiv

3D human pose lifting from a single RGB image is a challenging task in 3D vision. Existing methods typically establish a direct joint-to-joint mapping from 2D to 3D poses based on 2D features. This formulation suffers fr…

2D Pose Estimation