Anatomy and Geometry Constrained One-Stage Framework for 3D Human Pose Estimation

30/11/2020

Anatomy and Geometry Constrained One-Stage Framework for 3D Human Pose Estimation

Xin Cao, Xu Zhao

Keywords:

Abstract Paper Similar Papers

Abstract: Although significant progress has been achieved in monocular3D human pose estimation, the correlation between body parts andcross-view geometry consistency have not been well studied. In this work,to fully explore the priors on body structure and view-relationship for3D human pose estimation, we propose an anatomy and geometry constrainedone-stage framework. First of all, we define a kinematic structuremodel in deep learning framework which represents the joint positionsin a tree-structure model. Then we propose bone-length and bone-symmetrylosses based on the anatomy prior, to encode the body structureinformation. To further explore the cross-view geometry information,we introduce a novel training mechanism for multi-view consistencyconstraints, which effectively reduces unnatural and implausible estimationresults. The proposed approach achieves state-of-the-art results onboth Human3.6M and MPI-INF-3DHP data sets.

The video of this talk cannot be embedded. You can watch it here:

https://accv2020.github.io/miniconf/poster_18.html

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

22/11/2021

Unsupervised View-Invariant Human Posture Representation

Faegheh Sardari, Bjorn Ommer, Majid Mirmehdi

Keywords Paper

Representation Learning, Self-supervised Learning, Unsupervised 3D Pose Estimation, View-Invariant Pose Estimation, View-Invariant Action Recognition, View-Invariant Action Assessment, View-Invariant Human Movemnet Assessment, Human Posture Representation, Unsupervised Action Recognition, Unsupervised Action Assessment

0

0

0

0

2:59

02/02/2021

PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos

Tianyu Luan, Yali Wang, Junhao Zhang and
Zhe Wang, Zhipeng Zhou, Yu Qiao

Keywords Paper

0

0

0

0

14:32

02/02/2021

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

Yu Cheng, Bo Wang, Bo Yang, Robby T. Tan

Keywords Paper

0

0

0

0

15:02

14/06/2020

Detailed 2D-3D Joint Representation for Human-Object Interaction

Yong-Lu Li, Xinpeng Liu, Han Lu and
Shiyi Wang, Junqi Liu, Jiefeng Li, Cewu Lu

Keywords Paper

human-object interaction, multi-modal representation, single-view 3d recovering

0

0

0

0

1:01

06/12/2020

Continuous Surface Embeddings

Natalia Neverova, David Novotny, Marc Szafraniec and
Vasil Khalidov, Patrick Labatut, Andrea Vedaldi

Keywords Paper

0

0

0

0

3:03

25/07/2020

Pairwise view weighted graph network for view-based 3D model retrieval

Zan Gao, Yin-ming Li, Wei-li Guan and
Wei-zhi Nie, Zhi-yong Cheng, An-an Liu

Keywords Paper

non-local graph network, pairwise network architecture, view weighted layer, view-based 3D model retrieval

0

0

0

0

10:43

14/06/2020

Deep Kinematics Analysis for Monocular 3D Human Pose Estimation

Jingwei Xu, Zhenbo Yu, Bingbing Ni and
Jiancheng Yang, Xiaokang Yang, Wenjun Zhang

Keywords Paper

3d human pose estimation, kinematics, perspective projection

0

0

0

0

1:01

14/06/2020

Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data

Shichao Li, Lei Ke, Kevin Pratama and
Yu-Wing Tai, Chi-Keung Tang, Kwang-Ting Cheng

Keywords Paper

3d human pose estimation, data augmentation, evolution algorithm, 2d-to-3d network, high-resolution heatmap regression, generalization

0

0

0

0

4:59

07/09/2020

BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networks

Lixin Yang, Jiasen Li, Wenqiang Xu and
Yiqun Diao, Cewu Lu

Keywords Paper

hand pose estimation, 3d hand, hand reconstruction, hand mesh

0

0

0

0

5:30

14/06/2020

Learning Dynamic Relationships for 3D Human Motion Prediction

Qiongjie Cui, Huaijiang Sun, Fei Yang

Keywords Paper

human motion prediction, human motion capture data, human motion modeling, graph convolutional networks, generative adversarial networks

0

0

0

0

1:01

14/06/2020

Novel Object Viewpoint Estimation Through Reconstruction Alignment

Mohamed El Banani, Jason J. Corso, David F. Fouhey

Keywords Paper

viewpoint estimation, geometry-aware, alignment, reconstruction, 3d, cross-dataset, generalization

0

0

0

0

1:01

14/06/2020

Learning Deep Network for Detecting 3D Object Keypoints and 6D Poses

Wanqing Zhao, Shaobo Zhang, Ziyu Guan and
Wei Zhao, Jinye Peng, Jianping Fan

Keywords Paper

6d pose estimation, keypoints detection, relative pose, object detection, deep learning, computer vision, multi-task learning, metric learning, multi-view learning, epipolar geometry

0

0

0

0

1:01

14/06/2020

Unsupervised Learning of Intrinsic Structural Representation Points

Nenglun Chen, Lingjie Liu, Zhiming Cui and
Runnan Chen, Duygu Ceylan, Changhe Tu, Wenping Wang

Keywords Paper

3d point cloud learning, structure point, unsupervised learning

0

0

0

0

1:00

07/09/2020

Explicit Residual Descent for 3D Human Pose Estimation from 2D Joint Locations

Yangyuxuan Kang, Anbang Yao, Shandong Wang and
Ming Lu, Yurong Chen, Enhua Wu

Keywords Paper

3D human pose estimation, pose lifting network, feedback optimization, deep neural network, supervised learning

0

0

0

0

6:02

14/06/2020

Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

Jogendra Nath Kundu, Siddharth Seth, Varun Jampani and
Mugalodi Rakesh, R. Venkatesh Babu, Anirban Chakraborty

Keywords Paper

3d human pose estimation, self-supervised learning, disentangling factors of variation, human puppet model, pose transfer, novel view synthesis, human part segmentation

0

0

0

0

5:00

06/12/2021

Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

Ramesha Rakesh Mugaludi, Jogendra Nath Kundu, Varun Jampani, Venkatesh Babu R

Keywords Paper

vision, domain adaptation

0

0

0

0

12:03

30/11/2020

Learning 3D Face Reconstruction with a Pose Guidance Network

Pengpeng Liu, Xintong Han, Michael Lyu and
Irwin King, Jia Xu

Keywords Paper

0

0

0

0

9:32

06/12/2020

Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning

Huan Fu, Shunming Li, Rongfei Jia and
Mingming Gong, Binqiang Zhao, Dacheng Tao

Keywords Paper

0

0

0

0

3:21

07/09/2020

Advancing weakly supervised cross-domain alignment with optimal transport

Siyang Yuan, Ke Bai, Liqun Chen and
Yizhe Zhang, Chenyang Tao, Chunyuan Li, Guoyin Wang, Ricardo Henao, Lawrence Carin Duke

Keywords Paper

Optimal Transport, Cross Domain Alignment

0

0

0

0

10:04

14/06/2020

Three-Dimensional Reconstruction of Human Interactions

Mihai Fieraru, Mihai Zanfir, Elisabeta Oneata and
Alin-Ionut Popa, Vlad Olaru, Cristian Sminchisescu

Keywords Paper

human, interaction, 3d, reconstruction, contact, dataset, pose, shape, body, person

0

0

0

0

1:00

14/06/2020

Self-Supervised Learning of Interpretable Keypoints From Unlabelled Videos

Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi

Keywords Paper

self-supervised, unsupervised, keypoints, landmarks, pose, videos, adversarial, gan, disentanglement, factorizations

0

0

0

0

5:01

05/01/2021

Active Latent Space Shape Model: A Bayesian Treatment of Shape Model Adaptation With an Application to Psoriatic Arthritis Radiographs

Adwaye Rambojun, William Tillett, Tony Shardlow, Neill D. F. Campbell

Keywords Paper

0

0

0

0

3:20

06/12/2021

H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion

Hongyi Xu, Thiemo Alldieck, Cristian Sminchisescu

Keywords Paper

robustness

0

0

0

0

8:39

22/11/2021

Multi-Modality Task Cascade for 3D Object Detection

Jinhyung Park, Xinshuo Weng, Yunze Man, Kris Kitani

Keywords Paper

Multi Modality Learning, Object Detection, Semantic Segmentation

0

0

0

0

3:03

14/09/2020

Unsupervised Human Pose Estimation on Depth Images

Thibault Blanc Beyne, Axel Carlier, Sandrine Mouysset, Vincent Charvillat

Keywords Paper

depth images, unsupervised learning, human pose estimation, image-to-image translation

0

0

0

0

15:29

14/06/2020

Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence

Nicolas Donati, Abhishek Sharma, Maks Ovsjanikov

Keywords Paper

shape matching, 3d deep learning, functional maps, point clouds, computational geometry, 3d correspondence, 3d feature extraction

0

0

0

0

4:59

30/11/2020

Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation

Simon Jenni, Paolo Favaro

Keywords Paper

0

0

0

0

9:58

14/06/2020

GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning

Xinshuo Weng, Yongxin Wang, Yunze Man, Kris M. Kitani

Keywords Paper

autonomous driving, 3d multi-object tracking, graph neural networks, multi-agent state estimation, point cloud processing, multi-modal representation learning

0

0

0

0

1:01

05/01/2021

Self-Supervised 4D Spatio-Temporal Feature Learning via Order Prediction of Sequential Point Cloud Clips

Haiyan Wang, Liang Yang, Xuejian Rong and
Jinglun Feng, Yingli Tian

Keywords Paper

0

0

0

0

4:52

14/06/2020

How to Train Your Deep Multi-Object Tracker

Yihong Xu, Aljosa Osep, Yutong Ban and
Radu Horaud, Laura Leal-Taixé, Xavier Alameda-Pineda

Keywords Paper

deep multi-object tracking, mot end-to-end training, deep hungarian net, differentiable mota, differentiable motp, motchallenge benchmark, hungarian algorithm, vision-based tracking

0

0

0

0

1:01

22/11/2021

Learning Attention Map for 3D Human Recovery from a Single RGB Image

Peng Xu, Na Jiang, Jun Li, Zhiping Shi

Keywords Paper

3D Human Recover, Human Parsing, Depth Estimation

0

0

0

0

8:14

02/02/2021

Object-Centric Image Generation from Layouts

Tristan Sylvain, Pengchuan Zhang, Yoshua Bengio and
R Devon Hjelm, Shikhar Sharma

Keywords Paper

0

0

0

0

17:44

22/11/2021

Self-Supervised Monocular Depth Estimation with Internal Feature Fusion

Hang Zhou, David Greenwood, Sarah Taylor

Keywords Paper

depth estimation, structure from motion

0

0

0

0

2:49

22/11/2021

Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance

Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan, Alessio Del Bue

Keywords Paper

unsupervised learning, unsupervised action recognition, skeletal action recognition, skeleton action recognition, human action recognition, graph laplacian, viewpoint invariance

0

0

0

0

7:00

14/06/2020

Hierarchical Scene Coordinate Classification and Regression for Visual Localization

Xiaotian Li, Shuzhe Wang, Yi Zhao and
Jakob Verbeek, Juho Kannala

Keywords Paper

visual localization, camera relocalization, scene coordinate regression

0

0

0

0

1:01

02/02/2021

Learning Complex 3D Human Self-Contact

Mihai Fieraru, Mihai Zanfir, Elisabeta Oneata and
Alin-Ionut Popa, Vlad Olaru, Cristian Sminchisescu

Keywords Paper

0

0

0

0

18:09

06/12/2021

CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction

Leo Lebrat, Rodrigo Santa Cruz, Frederic de Gournay and
Darren Fu, Pierrick Bourgeat, Jurgen Fripp, Clinton Fookes, Olivier Salvado

Keywords Paper

deep learning, transformers

0

0

0

0

12:47

30/11/2020

3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

Giorgia Pitteri, Aureélie Bugeau, Slobodan Ilic, Vincent Lepetit

Keywords Paper

0

0

0

0

9:17

30/11/2020

Human Motion Deblurring using Localized Body Prior

Jonathan Samuel Lumentut, Joshua Santoso, In Kyu Park

Keywords Paper

0

0

0

0

7:57

14/06/2020

Self-Supervised Monocular Scene Flow Estimation

Junhwa Hur, Stefan Roth

Keywords Paper

monocular scene flow, self-supervised learning, 3d scene flow, optical flow, monocular depth estimation

0

0

0

0

5:00