Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision (2020-04-08T00:00:00.000000Z)

TL;DR

This work introduces a network that can be trained with additional RGB-D images in a weakly supervised fashion, and achieves state-of-the-art results on the MuPoTS-3D dataset by a considerable margin.

Abstract

In 3D human pose estimation one of the biggest problems is the lack of large, diverse datasets. This is especially true for multi-person 3D pose estimation, where, to our knowledge, there are only machine generated annotations available for training. To mitigate this issue, we introduce a network that can be trained with additional RGB-D images in a weakly supervised fashion. Due to the existence of cheap sensors, videos with depth maps are widely available, and our method can exploit a large, unannotated dataset. Our algorithm is a monocular, multi-person, absolute pose estimator. We evaluate the algorithm on several benchmarks, showing a consistent improvement in error rates. Also, our model achieves state-of-the-art results on the MuPoTS-3D dataset by a considerable margin.

Authors

M. Véges

2 papers

A. Lorincz

1 papers

TL;DR

Abstract

Authors

References39 items

Multi-Person 3D Human Pose Estimation from Monocular Images

Self-Supervised 3D Hand Pose Estimation Through Training by Fitting

Absolute Human Pose Estimation with Depth Prediction Network

Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network

Generalizing Monocular 3D Human Pose Estimation in the Wild

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

Deep High-Resolution Representation Learning for Human Pose Estimation

RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images

3D Human Pose Estimation with Siamese Equivariant Embedding

Weakly-Supervised 3D Hand Pose Estimation from Monocular RGB Images

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

Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes: The Importance of Multiple Scene Constraints

Ordinal Depth Supervision for 3D Human Pose Estimation

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

MegaDepth: Learning Single-View Depth Prediction from Internet Photos

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

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

LCR-Net: Localization-Classification-Regression for Human Pose

A Simple Yet Effective Baseline for 3d Human Pose Estimation

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

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

Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

Comparison of Kinect V1 and V2 Depth Images in Terms of Accuracy and Precision

Layer Normalization

RGBD Datasets: Past, Present and Future

Panoptic Studio: A Massively Multiview System for Social Motion Capture

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

3D Shape Reconstruction from 2D Landmarks: A Convex Formulation

3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network

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

3D Pictorial Structures for Multiple Human Pose Estimation

Reconstructing 3D Human Pose from 2D Image Landmarks

HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images

Mask R-CNN

Statistical methods for tomographic image reconstruction

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names