paper-with-me

Papers

Exploiting temporal context for 3D human pose estimation in the wild

2019-05-10 · CVPR 2019 6 · Anurag Arnab, Carl Doersch, Andrew Zisserman

We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence gives extra constraints that can resolve ambiguities. This is because videos often give multiple views of a person, yet the overall body shape does not change and 3D positions vary slowly. Our method improves not only on standard mocap-based datasets like Human 3.6M -- where we show quantitative improvements -- but also on challenging in-the-wild datasets such as Kinetics. Building upon our algorithm, we present a new dataset of more than 3 million frames of YouTube videos from Kinetics with automatically generated 3D poses and meshes. We show that retraining a single-frame 3D pose estimator on this data improves accuracy on both real-world and mocap data by evaluating on the 3DPW and HumanEVA datasets.

📄 PDF Abstract BibTeX arXiv:1905.04266

Code (1)

deepmind/Temporal-3D-Pose-Kinetics 공식 구현 tf

Tasks

3D Human Pose Estimation3D Pose EstimationMonocular 3D Human Pose EstimationPose Estimation

Similar Papers 제목 키워드 기반

Towards Accurate Human Pose Estimation in Videos of Crowded Scenes

2020-10-16 · Li Yuan, Shuning Chang, Xuecheng Nie, Ziyuan Huang 외

Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail to deal with this problem because of (1)…

DiversityOptical Flow EstimationPose Estimation

Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation

2025-12-06 · Haoxian Zhou, Chuanzhi Xu, Langyi Chen, Pengfei Ye 외 arxiv

Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and …

Computational EfficiencyPose Estimation

Exploiting temporal information for 3D human pose estimation

2018-09-01 · ECCV 2018 9 · Mir Rayat Imtiaz Hossain, James J. Little

In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep …

3D Human Pose Estimation3D Pose EstimationPose Estimation

Exploiting temporal information for 3D pose estimation

2017-11-23 · Mir Rayat Imtiaz Hossain, James J. Little

In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep …

3D Human Pose Estimation3D Pose EstimationDecoderPose Estimation

Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation

2021-03-26 · Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu 외

Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. T…

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation