3D Human Pose Estimation via Explicit Compositional Depth Maps

2020-02-08 · AAAI 2020 2 · Haiping Wu, Bin Xiao

n this work, we tackle the problem of estimating 3D human pose in camera space from a monocular image. First, we propose to use densely-generated limb depth maps to ease the learning of body joints depth, which are well aligned with image cues. Then, we design a lifting module from 2D pixel coordinates to 3D camera coordinates which explicitly takes the depth values as inputs, and is aligned with camera perspective projection model. We show our method achieves superior performance on large-scale 3D pose datasets Human3.6M and MPI-INF-3DHP, and sets the new state-of-the-art.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

3D Human Pose Estimation Pose Estimation

Attributed Grammars for Joint Estimation of Human Attributes, Part and Pose

2015-12-01 · ICCV 2015 12 · Se-Young Park, Song-Chun Zhu

In this paper, we are interested in developing compositional models to explicit representing pose, parts and attributes and tackling the tasks of attribute recognition, pose estimation and part localization jointly. Thi…

Attribute Human Parsing Pose Estimation

Deep Learning of Compositional Targets with Hierarchical Spectral Methods

2026-02-11 · Hugo Tabanelli, Yatin Dandi, Luca Pesce, Florent Krzakala arxiv

Why depth yields a genuine computational advantage over shallow methods remains a central open question in learning theory. We study this question in a controlled high-dimensional Gaussian setting, focusing on compositio…

PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation

2025-12-18 · Mengyuan Liu, Jiajie Liu, Jinyan Zhang, Wenhao Li 외 arxiv

The lifting-based methods have dominated monocular 3D human pose estimation by leveraging detected 2D poses as intermediate representations. The 2D component of the final 3D human pose benefits from the detected 2D poses…

Monocular 3D Human Pose Estimation 3D Pose Estimation

Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks

2020-04-09 · Tengyuan Liang, Hai Tran-Bach

We utilize a connection between compositional kernels and branching processes via Mehler's formula to study deep neural networks. This new probabilistic insight provides us a novel perspective on the mathematical role of…

Memorization

Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision

2018-09-21 · Kun Zhou, Jinmiao Cai, Yao Li, Yulong Shi 외

In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image. Specifically, a two-phase approach is developed. We firstly utilize a generator with two branches for the extr…