3D Human Motion Estimation via Motion Compression and Refinement

30/11/2020

3D Human Motion Estimation via Motion Compression and Refinement

Zhengyi Luo, S. Alireza Golestaneh, Kris M. Kitani

Keywords:

Abstract Paper Similar Papers

Abstract: We develop a technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences. Our technique, which we call Motion Estimation via Variational Autoencoder (MEVA), decomposes a temporal sequence of human motion into a smooth motion representation using auto-encoder-based motion compression and a residual representation learned through motion refinement. This two-step encoding process of human motion can represent a wide variety of general human motions while also retaining person-specific motion details. Experiments show that our method produces both smooth and accurate 3D human pose and motion estimates.

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

https://accv2020.github.io/miniconf/poster_697.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

06/12/2021

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs

Keywords Paper

transformers, vision

0

0

0

0

11:55

05/01/2021

Temporally Consistent 3D Human Pose Estimation Using Dual 360deg Cameras

Matthew Shere, Hansung Kim, Adrian Hilton

Keywords Paper

0

0

0

0

5:00

06/12/2021

Tracking People with 3D Representations

Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik

Keywords Paper

transformers

0

0

0

0

8:42

05/01/2021

Real-Time RGBD-Based Extended Body Pose Estimation

Renat Bashirov, Anastasia Ianina, Karim Iskakov and
Yevgeniy Kononenko, Valeriya Strizhkova, Victor Lempitsky, Alexander Vakhitov

Keywords Paper

0

0

0

0

4:53

14/06/2020

Sub-Frame Appearance and 6D Pose Estimation of Fast Moving Objects

Denys Rozumnyi, Jan Kotera, Filip Šroubek, Jiří Matas

Keywords Paper

fast moving objects, visual object tracking, 6d pose, trajectory estimation, deblatting, deblurring, matting, energy minimization

0

0

0

0

1:00

14/06/2020

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

Sena Kiciroglu, Helge Rhodin, Sudipta N. Sinha and
Mathieu Salzmann, Pascal Fua

Keywords Paper

viewpoint selection, human pose estimation, drone, camera positioning, mav, robotics, optimization, motion capture

0

0

0

0

5:01

22/11/2021

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation

Haoyu Ma, Liangjian Chen, Deying Kong and
Zhe Wang, Xingwei Liu, Hao Tang, Xiangyi Yan, Yusheng Xie, Shih-Yao Lin, Xiaohui Xie

Keywords Paper

multi-view, 3D pose estimation, epipolar line, vision transformer

0

0

0

0

3:01

14/06/2020

Combining Detection and Tracking for Human Pose Estimation in Videos

Manchen Wang, Joseph Tighe, Davide Modolo

Keywords Paper

human pose estimation in videos, pose tracking, video understanding, human understanding, 3d cnn, hrnet, posetrack

0

0

0

0

5:01

14/06/2020

DeepFaceFlow: In-the-Wild Dense 3D Facial Motion Estimation

Mohammad Rami Koujan, Anastasios Roussos, Stefanos Zafeiriou

Keywords Paper

3d flow, dense 3d facial motion capture, optical flow, scene flow, 3d reconstruction and tracking, in-the-wild monocular tracking, facial reenactment, expression recognition, performance capture, non-rigid facial deformations

0

0

0

0

1:01

06/12/2021

MAU: A Motion-Aware Unit for Video Prediction and Beyond

Zheng Chang, Xinfeng Zhang, Shanshe Wang and
Siwei Ma, Yan Ye, Xiang Xinguang, Wen Gao

Keywords Paper

vision

0

0

0

0

9:54

14/06/2020

Softmax Splatting for Video Frame Interpolation

Simon Niklaus, Feng Liu

Keywords Paper

video frame interpolation, softmax splatting, differentiable forward warping, feature pyramids for image synthesis

0

0

0

0

1:00

22/11/2021

Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image

Wenjing Bian, Zirui Wang, Kejie Li, Victor Adrian Prisacariu

Keywords Paper

3D reconstruction, shape representation, single-view reconstruction, occupancy networks, 3D deep learning

0

0

0

0

3:03

05/01/2021

Hand Pose Guided 3D Pooling for Word-Level Sign Language Recognition

Al Amin Hosain, Panneer Selvam Santhalingam, Parth Pathak and
Huzefa Rangwala, Jana Kosecka

Keywords Paper

0

0

0

0

4:39

14/06/2020

Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations

Alan Dolhasz, Carlo Harvey, Ian Williams

Keywords Paper

percetpion, jnd, vision, deep learning, image compositing, local distortions, subjective quality

0

0

0

0

1:01

26/04/2020

Image-guided Neural Object Rendering

Justus Thies, Michael Zollhöfer, Christian Theobalt and
Marc Stamminger, Matthias Nießner

Keywords Paper

Neural Rendering, Neural Image Synthesis

0

0

0

0

4:41

07/09/2020

Attentive Action and Context Factorization

Yang Wang, Vinh Tran, Gedas Bertasius and
Lorenzo Torresani, Minh Hoai Nguyen

Keywords Paper

action factorization, attention, conjugate samples

0

0

0

0

9:59

06/12/2021

Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding

Yang Li, Si Si, Gang Li and
Cho-Jui Hsieh, Samy Bengio

Keywords Paper

machine learning, transformers, vision

0

0

0

0

10:54

02/02/2021

Activity Image-to-Video Retrieval by Disentangling Appearance and Motion

Liu Liu, Jiangtong Li, Li Niu and
Ruicong Xu, Liqing Zhang

Keywords Paper

0

0

0

1

14:34

30/11/2020

Recursive Bayesian Filtering for Multiple Human Pose Tracking from Multiple Cameras

Oh-Hun Kwon, Julian Tanke, Jürgen Gall

Keywords Paper

0

0

0

0

9:33

02/02/2021

Temporal ROI Align for Video Object Recognition

Tao Gong, Kai Chen, Xinjiang Wang and
Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng

Keywords Paper

0

0

0

0

14:29

06/12/2021

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers

Aljaz Bozic, Pablo Palafox, Justus Thies and
Angela Dai, Matthias Niessner

Keywords Paper

transformers

0

0

0

0

7:14

14/06/2020

Bayesian Adversarial Human Motion Synthesis

Rui Zhao, Hui Su, Qiang Ji

Keywords Paper

probabilistic graphical model, adversarial learning, bayesian inference, data synthesis, data restoration, motion capture, human dynamics

0

0

0

0

5:00

14/06/2020

HUMBI: A Large Multiview Dataset of Human Body Expressions

Zhixuan Yu, Jae Shin Yoon, In Kyu Lee and
Prashanth Venkatesh, Jaesik Park, Jihun Yu, Hyun Soo Park

Keywords Paper

human, expression, dataset, multiview, gaze, face, hand, body, garment, appearance

0

0

0

0

1:00

30/11/2020

Visually Guided Sound Source Separation using Cascaded Opponent Filter Network

Lingyu Zhu, Esa Rahtu

Keywords Paper

0

0

0

0

7:38

14/06/2020

TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

Zhuoqian Yang, Wentao Zhu, Wayne Wu and
Chen Qian, Qiang Zhou, Bolei Zhou, Chen Change Loy

Keywords Paper

motion retargeting, disentanglement, representation learning, video generation

0

0

0

0

1:02

05/01/2021

MART: Motion-Aware Recurrent Neural Network for Robust Visual Tracking

Heng Fan, Haibin Ling

Keywords Paper

0

0

0

0

4:55

22/11/2021

V3GAN: Decomposing Background, Foreground and Motion for Video Generation

Arti Keshari, Sonam Gupta, Sukhendu Das

Keywords Paper

video generation, unconditional video generation, shuffling loss, feature level masking, unsupervised learning, GAN, foreground, background, motion decomposition

0

0

0

0

3:02

06/12/2021

Panoptic 3D Scene Reconstruction From a Single RGB Image

Manuel Dahnert, Ji Hou, Matthias Niessner, Angela Dai

Keywords Paper

vision

0

0

0

0

6:06

14/06/2020

Epipolar Transformers

Yihui He, Rui Yan, Katerina Fragkiadaki, Shoou-I Yu

Keywords Paper

keypoint detection, pose estimation, epipolar geometry, attention, transformer, non-local networks

0

0

0

0

1:00

14/06/2020

On Joint Estimation of Pose, Geometry and svBRDF From a Handheld Scanner

Carolin Schmitt, Simon Donné, Gernot Riegler and
Vladlen Koltun, Andreas Geiger

Keywords Paper

3d reconstruction, mobile lightstage, mulitview photometric stereo, svbrdf estimation, shape from shading, material segmentation, handheld 3d sensor, non-lambertian surfaces

0

0

0

0

1:01

14/06/2020

Time Flies: Animating a Still Image With Time-Lapse Video As Reference

Chia-Chi Cheng, Hung-Yu Chen, Wei-Chen Chiu

Keywords Paper

time-lapse video animation, self-supervised learning, style transfer, temporal consistency

0

0

0

0

1:01

22/11/2021

Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE

Kangyeol Kim, Sunghyun Park, Junsoo Lee and
Joonseok Lee, Sookyung Kim, Jaegul Choo, Edward Choi

Keywords Paper

video generation, generative model, neural ODE, motion estimation

0

0

0

0

2:46

02/02/2021

Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation

Lincheng Li, Suzhen Wang, Zhimeng Zhang and
Yu Ding, Yixing Zheng, Xin Yu, Changjie Fan

Keywords Paper

0

0

0

0

15:58

05/01/2021

Cinematic-L1 Video Stabilization With a Log-Homography Model

Arwen Bradley, Jason Klivington, Joseph Triscari, Rudolph van der Merwe

Keywords Paper

0

0

0

0

5:01

14/06/2020

Extreme Relative Pose Network Under Hybrid Representations

Zhenpei Yang, Siming Yan, Qixing Huang

Keywords Paper

relative pose estimation, rgb-d registration, few shot reconstruction, hybrid representation

0

0

0

0

4:56

02/02/2021

Motion-blurred Video Interpolation and Extrapolation

Dawit Mureja Argaw, Junsik Kim, Francois Rameau, In So Kweon

Keywords Paper

0

0

0

0

17:28

14/06/2020

GaitPart: Temporal Part-Based Model for Gait Recognition

Chao Fan, Yunjie Peng, Chunshui Cao and
Xu Liu, Saihui Hou, Jiannan Chi, Yongzhen Huang, Qing Li, Zhiqiang He

Keywords Paper

gait recognition, part-based model, temporal model, deep learning

0

0

0

0

1:01

14/06/2020

G3AN: Disentangling Appearance and Motion for Video Generation

Yaohui Wang, Piotr Bilinski, Francois Bremond, Antitza Dantcheva

Keywords Paper

generative adversarial networks, video generation, disentanglement learning, face generation, image and video synthesis, spatio-temporal modeling, generative model, representation learning, attention mechanism, emotion generation

0

0

0

0

1:01

05/01/2021

Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition

Zachary Wharton, Ardhendu Behera, Yonghuai Liu, Nik Bessis

Keywords Paper

0

0

0

0

5:30

06/12/2021

End-to-end Multi-modal Video Temporal Grounding

Yi-Wen Chen, Yi-Hsuan Tsai, Ming-Hsuan Yang

Keywords Paper

self-supervised learning, transformers, vision, contrastive learning

0

0

0

0

8:46