It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
원문 초록
We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data. Despite showing considerable success for 2D pose estimation, the application of supervised machine learning to 3D pose estimation in real world images is currently hampered by the lack of varied training images with corresponding 3D poses. Most existing 3D pose estimation algorithms train on data that has either been collected in carefully controlled studio settings or has been generated synthetically. Instead, we take a different approach, and propose a 3D human pose estimation algorithm that only requires relative estimates of depth at training time. Such training signal, although noisy, can be easily collected from crowd annotators, and is of sufficient quality for enabling successful training and evaluation of 3D pose algorithms. Our results are competitive with fully supervised regression based approaches on the Human3.6M dataset, despite using significantly weaker training data. Our proposed algorithm opens the door to using existing widespread 2D datasets for 3D pose estimation by allowing fine-tuning with noisy relative constraints, resulting in more accurate 3D poses.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation
Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation
AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements
DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion
Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.