Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Hanbyul Joo

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

Nov 02, 2020
Benjamin Biggs, Sébastien Ehrhadt, Hanbyul Joo, Benjamin Graham, Andrea Vedaldi, David Novotny

* NeurIPS 2020 Spotlight; 14 pages including supplementary 

  Access Paper or Ask Questions

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

Aug 19, 2020
Jason Y. Zhang, Sam Pepose, Hanbyul Joo, Deva Ramanan, Jitendra Malik, Angjoo Kanazawa

* In ECCV 2020. v2: Updated Related Work 

  Access Paper or Ask Questions

FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration

Aug 19, 2020
Yu Rong, Takaaki Shiratori, Hanbyul Joo

* Demo, Code and Models are available at 

  Access Paper or Ask Questions

Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics

Jul 23, 2020
Evonne Ng, Hanbyul Joo, Shiry Ginosar, Trevor Darrell

  Access Paper or Ask Questions

Exemplar Fine-Tuning for 3D Human Pose Fitting Towards In-the-Wild 3D Human Pose Estimation

Apr 07, 2020
Hanbyul Joo, Natalia Neverova, Andrea Vedaldi

  Access Paper or Ask Questions

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

Apr 01, 2020
Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo

* The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 
* project page: 

  Access Paper or Ask Questions

Single-Network Whole-Body Pose Estimation

Sep 30, 2019
Gines Hidalgo, Yaadhav Raaj, Haroon Idrees, Donglai Xiang, Hanbyul Joo, Tomas Simon, Yaser Sheikh

* ICCV 2019 

  Access Paper or Ask Questions

Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction

Jun 10, 2019
Hanbyul Joo, Tomas Simon, Mina Cikara, Yaser Sheikh

* CVPR 2019 

  Access Paper or Ask Questions

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

Apr 22, 2019
Evonne Ng, Donglai Xiang, Hanbyul Joo, Kristen Grauman

  Access Paper or Ask Questions

Capture Dense: Markerless Motion Capture Meets Dense Pose Estimation

Dec 11, 2018
Xiu Li, Yebin Liu, Hanbyul Joo, Qionghai Dai, Yaser Sheikh

* Withdraw due to incomplete experiment 

  Access Paper or Ask Questions

Monocular Total Capture: Posing Face, Body, and Hands in the Wild

Dec 04, 2018
Donglai Xiang, Hanbyul Joo, Yaser Sheikh

* 17 pages, 16 figures 

  Access Paper or Ask Questions

Structure from Recurrent Motion: From Rigidity to Recurrency

Apr 18, 2018
Xiu Li, Hongdong Li, Hanbyul Joo, Yebin Liu, Yaser Sheikh

* To appear in CVPR 2018 

  Access Paper or Ask Questions

Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies

Jan 05, 2018
Hanbyul Joo, Tomas Simon, Yaser Sheikh

  Access Paper or Ask Questions

Hand Keypoint Detection in Single Images using Multiview Bootstrapping

Apr 25, 2017
Tomas Simon, Hanbyul Joo, Iain Matthews, Yaser Sheikh

* CVPR 2017 

  Access Paper or Ask Questions

Panoptic Studio: A Massively Multiview System for Social Interaction Capture

Dec 09, 2016
Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, Yaser Sheikh

* Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence 

  Access Paper or Ask Questions