Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People (2020-10-31T00:00:00.000000Z)

TL;DR

This work presents an energy minimization approach to generate smooth, valid trajectories in time, bridging gaps in visibility in multi-person pose estimation, and shows that it is better than other interpolation based approaches and achieves state of the art results.

Abstract

In multi-person pose estimation actors can be heavily occluded, even become fully invisible behind another person. While temporal methods can still predict a reasonable estimation for a temporarily disappeared pose using past and future frames, they exhibit large errors nevertheless. We present an energy minimization approach to generate smooth, valid trajectories in time, bridging gaps in visibility. We show that it is better than other interpolation based approaches and achieves state of the art results. In addition, we present the synthetic MuCo-Temp dataset, a temporal extension of the MuCo-3DHP dataset. Our code is made publicly available.

Authors

M. Véges

2 papers

András Lörincz

1 papers

TL;DR

Abstract

Authors

References36 items

Motion Guided 3D Pose Estimation from Videos

Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision

Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints

Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

Occlusion-Aware Networks for 3D Human Pose Estimation in Video

Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation

Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image

Cross View Fusion for 3D Human Pose Estimation

Exploiting Temporal Context for 3D Human Pose Estimation in the Wild

Absolute Human Pose Estimation with Depth Prediction Network

Semantic Graph Convolutional Networks for 3D Human Pose Regression

Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry

Deep High-Resolution Representation Learning for Human Pose Estimation

3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training

Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation

Propagating LSTM: 3D Pose Estimation Based on Joint Interdependency

Can 3D Pose be Learned from 2D Projections Alone?

Ordinal Depth Supervision for 3D Human Pose Estimation

Learning Monocular 3D Human Pose Estimation from Multi-view Images

LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning

Single-Shot Multi-person 3D Pose Estimation from Monocular RGB

Exploiting Temporal Information for 3D Human Pose Estimation

Integral Human Pose Regression

Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

A Simple Yet Effective Baseline for 3d Human Pose Estimation

VNect

Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

Compositional Human Pose Regression

Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision

Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments

3D Pictorial Structures for Multiple Human Pose Estimation

Microsoft COCO: Common Objects in Context

Reconstructing 3D Human Pose from 2D Image Landmarks

1 € filter: a simple speed-based low-pass filter for noisy input in interactive systems

Exploiting temporal information for 3D pose estimation

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names